© 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. 10-GEMMASCOPE-RES-131K
    7. 21977
    Prev
    Next
    INDEX
    Explanations

    lists or items

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

    This neuron responds to numeric literals (numbers, numeric constants, or numeric tokens) in code or 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_10/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
     nimmer
    -1.68
     Forse
    -1.66
     ſy
    -1.63
    嗫
    -1.61
    ><><
    -1.59
     schuld
    -1.59
    einander
    -1.58
    簡単に
    -1.58
     หลัง
    -1.54
    すぎて
    -1.53
    POSITIVE LOGITS
     there
    1.97
     of
    1.87
    *
    1.81
     they
    1.78
    end
    1.73
     how
    1.73
    O
    1.72
     people
    1.70
    M
    1.67
     it
    1.63
    Activations Density 0.001%

    No Known Activations