© 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. 8050
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

    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
    های
    -1.75
    ﹍﹍
    -1.68
    嚆
    -1.67
    鲼
    -1.67
    already
    -1.65
    𓁹
    -1.65
     derrière
    -1.64
    ين
    -1.64
    ᯾
    -1.63
     pérd
    -1.61
    POSITIVE LOGITS
     for
    1.94
     about
    1.88
     shown
    1.60
     between
    1.55
     in
    1.55
     taken
    1.49
     on
    1.48
     of
    1.48
    ではありません
    1.47
     playing
    1.44
    Activations Density 0.004%

    No Known Activations