© 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. 64701
    Prev
    Next
    INDEX
    Explanations

    episode of

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

    The neuron activates on numeric tokens (sequences 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_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
     were
    -2.97
    '
    -2.52
    $,
    -2.34
    ;
    -2.31
    A
    -2.30
    ︲
    -2.25
    >
    -2.19
     lebte
    -2.16
    4
    -2.08
    ."
    -2.03
    POSITIVE LOGITS
    ↵
    2.42
    哢
    2.13
    ’，
    2.11
     від
    1.94
    Wady
    1.93
    ///////
    1.88
    难过
    1.87
     was
    1.86
    鸰
    1.84
    潜力
    1.80
    Activations Density 0.011%

    No Known Activations