© 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. 22-GEMMASCOPE-RES-131K
    7. 34208
    Prev
    Next
    INDEX
    Explanations

    Federal legislation RS

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

    The neuron principally detects numeric tokens (i.e. numbers and digit sequences) in the text.

    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
    *}
    -0.90
    pedal
    -0.84
    icam
    -0.83
    Condition
    -0.82
    journ
    -0.81
    zeitige
    -0.81
     twarzy
    -0.81
     环境
    -0.81
    ::::::::
    -0.80
     Technician
    -0.80
    POSITIVE LOGITS
     time
    0.85
    举例
    0.84
    何と
    0.82
    ATIVES
    0.80
     refined
    0.77
     Mic
    0.73
    ANDUM
    0.73
    czył
    0.73
    การณ์
    0.73
    んですね
    0.73
    Activations Density 0.046%

    No Known Activations