© 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. 65750
    Prev
    Next
    INDEX
    Explanations

    graded degree length

    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
     the
    -1.00
     bēr
    -1.00
     MODERN
    -0.95
     også
    -0.93
     November
    -0.93
     January
    -0.93
    ^{*}$
    -0.91
    Qur
    -0.90
     Child
    -0.90
     garganta
    -0.87
    POSITIVE LOGITS
    Ύ
    1.01
    ripsi
    0.97
    देश
    0.97
    уза
    0.95
    éis
    0.94
    sság
    0.92
     dass
    0.92
    الية
    0.91
     фильтр
    0.91
    ();
    0.91
    Activations Density 0.020%

    No Known Activations