© 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. 128744
    Prev
    Next
    INDEX
    Explanations

    The neuron responds to tokens that are numeric literals (multi‐digit numbers or numeric strings), i.e. it flags numeric constants in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    numerical sequences and separators

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    樟
    -0.93
    blockList
    -0.85
    стую
    -0.84
    ℠
    -0.84
    ztály
    -0.83
    lawan
    -0.83
    }],
    -0.82
    emark
    -0.82
     που
    -0.79
     samt
    -0.78
    POSITIVE LOGITS
     another
    0.98
     also
    0.97
     same
    0.96
    /
    0.95
     pouvez
    0.92
     second
    0.89
     later
    0.88
     further
    0.88
     другой
    0.86
    タメ
    0.85
    Activations Density 0.035%

    No Known Activations