© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77879
    Prev
    Next
    INDEX
    Explanations

    Lung donation

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

    code license and copyright statements in software headers.

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

    The neuron fires on numeric tokens—i.e. any sequence of digits.

    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
    )(-
    -0.82
    大野
    -0.81
     mógł
    -0.76
    堇
    -0.76
    منی
    -0.72
     nướng
    -0.72
     manzana
    -0.71
     consultas
    -0.71
     materials
    -0.70
     cloning
    -0.70
    POSITIVE LOGITS
     عليهم
    0.81
     INTER
    0.71
    apunov
    0.71
     Spart
    0.71
     Kond
    0.71
     pram
    0.71
     пан
    0.70
    moy
    0.68
     kado
    0.67
    ided
    0.67
    Activations Density 0.026%

    No Known Activations