© 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. 113702
    Prev
    Next
    INDEX
    Explanations

    essential components or roles

    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
    旆
    -3.48
     появляется
    -2.94
    ༀ
    -2.83
    瑨
    -2.67
    ांकि
    -2.59
    厹
    -2.47
    BITDA
    -2.45
    罽
    -2.39
    氿
    -2.33
    乸
    -2.33
    POSITIVE LOGITS
    \
    3.11
    (
    3.02
    It
    2.98
    ?”
    2.70
    8
    2.69
    .
    2.55
    5
    2.53
    This
    2.52
    We
    2.44
    There
    2.44
    Activations Density 0.000%

    No Known Activations