© 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. 33999
    Prev
    Next
    INDEX
    Explanations

    organizations and entities

    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
     his
    -1.14
     dessa
    -1.09
     serum
    -1.05
     a
    -1.03
    .*;
    -1.02
    kmäler
    -1.01
    VideoCapture
    -1.00
    .~(\
    -0.99
     ocurrió
    -0.98
     deine
    -0.97
    POSITIVE LOGITS
    Gets
    1.13
     fundamento
    1.02
     préféré
    0.99
     souhaitent
    0.99
    معرفی
    0.98
    诸多
    0.98
     genoux
    0.97
     нравится
    0.97
    を与える
    0.96
    打量
    0.96
    Activations Density 0.003%

    No Known Activations