© 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. 73606
    Prev
    Next
    INDEX
    Explanations

    Q: or starting number/word

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

    The neuron primarily detects asterisk characters (e.g., “*”).

    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
     it
    -2.00
    経由
    -1.34
     was
    -1.31
     its
    -1.30
    </strong>
    -1.30
     recientemente
    -1.30
    rozco
    -1.29
     что
    -1.29
     or
    -1.28
     где
    -1.26
    POSITIVE LOGITS
    komendasi
    1.56
    ♮
    1.52
    $.
    1.50
     município
    1.49
    JAMIN
    1.48
    LAHOMA
    1.48
    ⸗
    1.47
     शुर
    1.45
     stata
    1.45
     Akad
    1.44
    Activations Density 0.000%

    No Known Activations