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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34693
    Prev
    Next
    INDEX
    Explanations

    various chemical prefixes/suffixes

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

    technical notation and syntax in specialized documents such as code, mathematical expressions, and scientific texts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is keyed to numeric tokens and measurements—i.e. it fires strongly on digits, counts, and other numeric values.

    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
    FIA
    -0.89
    Warum
    -0.87
    tagez
    -0.84
    forEach
    -0.84
    dı
    -0.82
    ‭
    -0.81
    ٧
    -0.81
    Soorten
    -0.78
     Nantes
    -0.78
    Fellow
    -0.78
    POSITIVE LOGITS
    𝖍
    0.90
     pensamento
    0.90
     céu
    0.86
     século
    0.85
    说实话
    0.84
     sonho
    0.84
     detalhe
    0.83
     esforço
    0.82
     silêncio
    0.82
     blocco
    0.81
    Activations Density 0.081%

    No Known Activations