© 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. 65182
    Prev
    Next
    INDEX
    Explanations

    numbers and underscores

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

    The neuron strongly activates on standalone numeric tokens or numeric literals (e.g. version numbers, table suffixes, constants) in code or markup.

    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
    缽
    -1.02
    üyü
    -0.97
     survival
    -0.95
    andidat
    -0.94
    pina
    -0.93
    niveau
    -0.93
    kenal
    -0.92
    ikistan
    -0.92
    IFORNIA
    -0.91
    зак
    -0.91
    POSITIVE LOGITS
    y
    0.93
    ʼ
    0.92
    er
    0.90
     unseres
    0.89
    '
    0.88
    iv
    0.87
    ão
    0.85
    os
    0.85
    ore
    0.85
    ong
    0.84
    Activations Density 0.002%

    No Known Activations