© 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. 63214
    Prev
    Next
    INDEX
    Explanations

    protocol entities

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

    The neuron activates on numerical tokens—i.e. standalone numbers or 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
     refuses
    -0.73
     furnishes
    -0.71
    влаж
    -0.69
    osoma
    -0.68
     ở
    -0.68
    鯵
    -0.66
    mler
    -0.66
    Glas
    -0.66
     MHD
    -0.66
    Eug
    -0.65
    POSITIVE LOGITS
    iële
    0.71
     Lama
    0.67
    ANTIC
    0.67
    ICAO
    0.67
    غو
    0.65
    大陸
    0.64
    گو
    0.64
    SEL
    0.63
    vats
    0.63
    pier
    0.63
    Activations Density 0.107%

    No Known Activations