© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 71271
    Prev
    Next
    INDEX
    Explanations

    only and not

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

    This neuron fires on common discourse/connective words—especially adverbs and modals that signal emphasis or addition (e.g. “also,” “just,” “about,” “forget,” “could”).

    oai_token-act-pair · o4-miniTriggered 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
    の人に
    -1.34
     أثناء
    -1.22
    Thiết
    -1.07
     muchacho
    -1.07
     atendido
    -1.07
    総評
    -1.05
     dokonce
    -1.03
    — 
    -1.02
    先生が
    -1.01
    のお客様
    -0.99
    POSITIVE LOGITS
     anything
    1.77
     something
    1.46
     some
    1.32
     any
    1.24
    各种
    1.22
     those
    1.12
     including
    1.10
    anything
    1.09
    Anything
    1.09
     various
    1.08
    Activations Density 0.057%

    No Known Activations