© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127338
    Prev
    Next
    INDEX
    Explanations

    also/still followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects discourse‐linking adverbs—especially “also” (and similarly “still”) when used to connect clauses.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    constructions where a clause opened by a simultaneity/concessive marker is immediately followed by an additive or continuative adverb to express an additional action occurring at the same time.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the phrase "while also" when it connects two parallel or simultaneous actions or purposes.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     when
    -2.41
     after
    -2.33
     that
    -2.33
     more
    -2.25
     before
    -2.16
     what
    -2.13
     want
    -2.11
    in
    -2.06
     to
    -2.05
     only
    -2.03
    POSITIVE LOGITS
    轳
    2.30
    ícias
    2.20
    佧
    2.16
    熥
    2.16
     ſta
    2.14
    𖧵
    2.13
     raiſ
    2.08
    𖣘
    2.00
    埽
    2.00
    甍
    1.99
    Activations Density 0.002%

    No Known Activations