© 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. 71307
    Prev
    Next
    INDEX
    Explanations

    value to wrap

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

    The neuron primarily detects numeric literals (numbers) embedded in the code or documentation.

    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
    Funciones
    -1.76
    ELTS
    -1.74
     cepillo
    -1.73
    UPAC
    -1.61
    bsen
    -1.59
    ⚌
    -1.51
    carus
    -1.49
    凵
    -1.44
    dding
    -1.44
    athered
    -1.44
    POSITIVE LOGITS
     from
    1.88
    0
    1.71
    While
    1.66
    After
    1.63
    Despite
    1.60
    When
    1.57
    From
    1.57
    Almost
    1.55
    There
    1.52
    there
    1.52
    Activations Density 0.013%

    No Known Activations