© 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. 68109
    Prev
    Next
    INDEX
    Explanations

    bool checks

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     sufrido
    -1.44
    ￦
    -1.39
     from
    -1.39
    🍼
    -1.37
    odios
    -1.37
    他对
    -1.36
    他还
    -1.35
    不断的
    -1.32
    ALLED
    -1.30
    Ꮞ
    -1.30
    POSITIVE LOGITS
     then
    1.95
    2
    1.90
    8
    1.70
    4
    1.55
    6
    1.53
    This
    1.38
    ;
    1.37
    9
    1.34
    VILLE
    1.34
    or
    1.34
    Activations Density 0.047%

    No Known Activations