© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 19173
    Prev
    Next
    INDEX
    Explanations

    prefix identifiers and code structure

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

    The neuron activates on literal number tokens (numeric constants) in code.

    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
    sistence
    -1.69
    螃
    -1.63
    født
    -1.63
     deberían
    -1.57
     เรา
    -1.55
     EACH
    -1.55
    quirer
    -1.55
    ⽼
    -1.55
    cadeau
    -1.54
     produttore
    -1.53
    POSITIVE LOGITS
     with
    2.42
     was
    2.14
     for
    1.99
     a
    1.80
    '
    1.78
    For
    1.66
    At
    1.66
    With
    1.63
     also
    1.62
    but
    1.61
    Activations Density 0.063%

    No Known Activations