© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 40170
    Prev
    Next
    INDEX
    Explanations

    ranges and separators

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

    The neuron activates on numeric tokens (digits, numbers, or numeric expressions such as integers and decimals).

    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
    *{-
    -2.06
     kroppen
    -2.06
     problemet
    -1.98
     Februari
    -1.95
    存知
    -1.95
    :")
    -1.94
     ideen
    -1.93
     edile
    -1.93
    lerim
    -1.91
    櫺
    -1.91
    POSITIVE LOGITS
     are
    2.88
     a
    2.83
     I
    2.38
     was
    2.33
     from
    2.23
     but
    2.13
     part
    2.06
     called
    2.00
     Another
    1.93
     known
    1.92
    Activations Density 0.014%

    No Known Activations