© 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. 34-GEMMASCOPE-RES-131K
    7. 116894
    Prev
    Next
    INDEX
    Explanations

    medical or scientific contexts

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

    machine learning and algorithm terms in code contexts.

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

    The neuron strongly activates on numeric tokens (digits and numeric literals) in code, such as parameter values, array indices, and numeric constants.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    大笑
    -0.76
     Massey
    -0.75
    Ưu
    -0.74
     Razor
    -0.73
    思念
    -0.73
    ʎ
    -0.71
     sueldo
    -0.70
     Forestry
    -0.70
     hoteles
    -0.69
    dbh
    -0.69
    POSITIVE LOGITS
     callable
    0.84
    зен
    0.82
    solver
    0.81
    callable
    0.81
    job
    0.79
    hiki
    0.79
    よりも
    0.77
    =,
    0.76
     estimator
    0.76
     solver
    0.76
    Activations Density 0.007%

    No Known Activations