© 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. 16243
    Prev
    Next
    INDEX
    Explanations

    legal cases for parties

    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
     plafon
    -1.34
     mochila
    -1.29
     inaugura
    -1.23
     ofert
    -1.23
     baratas
    -1.20
     saco
    -1.20
     bicicleta
    -1.19
     charla
    -1.17
     sois
    -1.17
     cintur
    -1.17
    POSITIVE LOGITS
     but
    1.03
     proposte
    1.00
    b
    0.96
    N
    0.96
     indicó
    0.96
    u
    0.94
     añadió
    0.94
     asemenea
    0.93
    g
    0.92
    ur
    0.91
    Activations Density 0.003%

    No Known Activations