© 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. 68116
    Prev
    Next
    INDEX
    Explanations

    colon or dash then capitalized word

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

    This neuron responds to numeric values that label or quantify sections (e.g. numbers following headings or list items).

    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
     คา
    -1.95
    …»
    -1.86
    ㅡ
    -1.81
    ...',
    -1.75
     klubben
    -1.69
    ...»
    -1.68
    …]
    -1.65
    wwwwwwww
    -1.64
     marchandises
    -1.64
     and
    -1.64
    POSITIVE LOGITS
     in
    2.91
     since
    2.75
     despite
    2.47
     Since
    2.31
     there
    2.25
     because
    2.25
     although
    2.16
     when
    2.16
     It
    2.13
     Despite
    2.08
    Activations Density 0.009%

    No Known Activations