© 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. 67794
    Prev
    Next
    INDEX
    Explanations

    by the name

    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
    ↵↵↵
    -1.58
    苼
    -1.48
    </em>
    -1.34
    ть
    -1.34
    jší
    -1.34
    vartis
    -1.31
     trhu
    -1.30
    са
    -1.30
    ба
    -1.28
     sagrada
    -1.27
    POSITIVE LOGITS
     name
    2.77
     to
    1.97
     names
    1.77
    ชื่อ
    1.52
     the
    1.49
    ！】
    1.46
     cercanos
    1.37
     verbinding
    1.37
     disfrutando
    1.34
    name
    1.30
    Activations Density 0.164%

    No Known Activations