© 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. 128654
    Prev
    Next
    INDEX
    Explanations

    points and repetition counts

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

    The neuron primarily responds to numeric tokens (scores, statistics, and other number sequences).

    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
     presque
    -1.84
     soportes
    -1.74
     semblent
    -1.74
    𓁹
    -1.73
    ཿ
    -1.70
     delightfully
    -1.70
    
    -1.70
     bocetos
    -1.67
     decidedly
    -1.66
    LANDS
    -1.66
    POSITIVE LOGITS
     our
    2.36
     this
    2.14
     any
    1.94
     during
    1.84
     of
    1.84
     by
    1.78
     in
    1.73
    二日
    1.71
     because
    1.70
     when
    1.63
    Activations Density 0.048%

    No Known Activations