© 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. 33298
    Prev
    Next
    INDEX
    Explanations

    famous people's 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
    chenken
    -1.05
    Asociación
    -1.00
    tise
    -0.99
     nedenle
    -0.99
     insiste
    -0.99
    RICAL
    -0.98
     dopiero
    -0.98
    ならでは
    -0.97
     ausgeschlossen
    -0.96
     mężczyzn
    -0.96
    POSITIVE LOGITS
    若干
    1.09
     on
    0.98
     in
    0.97
     quotes
    0.95
    而后
    0.91
    糧
    0.91
    念头
    0.91
     milieux
    0.90
    謁
    0.89
    埽
    0.89
    Activations Density 0.033%

    No Known Activations