© 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. 65160
    Prev
    Next
    INDEX
    Explanations

    license, March Madness, names

    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
    Kegiatan
    -1.09
    Tentang
    -1.05
    shops
    -0.97
    ắn
    -0.96
    grafos
    -0.94
    arschijnlijk
    -0.92
     automobili
    -0.91
    殒
    -0.91
     auc
    -0.90
     palestra
    -0.90
    POSITIVE LOGITS
     различных
    1.09
    creativecommons
    1.02
    <tr>
    0.98
    BRACE
    0.95
     secretos
    0.94
    alace
    0.94
     I
    0.93
     тук
    0.93
    WEBPACK
    0.93
    MAY
    0.93
    Activations Density 0.000%

    No Known Activations