© 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. 22-GEMMASCOPE-RES-131K
    7. 65908
    Prev
    Next
    INDEX
    Explanations

    plugin, code, or specific phrases

    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_22/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
     then
    -1.08
     again
    -1.02
    を見ると
    -0.94
    og
    -0.93
    pwr
    -0.92
    bing
    -0.86
     apoi
    -0.85
    ographed
    -0.85
    GroupBox
    -0.84
    checkIf
    -0.82
    POSITIVE LOGITS
     mengucap
    0.98
     promosi
    0.98
     your
    0.98
     menonton
    0.97
     you
    0.97
     many
    0.96
     AllMovie
    0.90
    ʷ
    0.90
     liburan
    0.90
    签
    0.89
    Activations Density 0.000%

    No Known Activations