© 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. 22-GEMMASCOPE-RES-131K
    7. 66550
    Prev
    Next
    INDEX
    Explanations

    what remains or is wanted

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

    The neuron detects words or short phrases that appear inside quotation marks.

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

    phrases expressing contrast or opposition between two states or perspectives, particularly in the form "being X" or "X versus Y" constructions.

    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_22/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
    Gön
    -1.34
     solche
    -1.23
     senhora
    -1.14
     conceito
    -1.13
     trabalhar
    -1.11
    綺麗な
    -1.09
    に対する
    -1.09
     poderia
    -1.09
     detayl
    -1.09
     your
    -1.07
    POSITIVE LOGITS
     what
    1.44
    *',
    1.34
     which
    1.29
     as
    1.26
    😲
    1.21
     newBuilder
    1.20
    或
    1.20
     or
    1.20
    +',
    1.13
    ↵
    1.12
    Activations Density 0.040%

    No Known Activations