© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16465
    Prev
    Next
    INDEX
    Explanations

    you or your

    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
     teclas
    -1.06
    masin
    -1.04
     Reglas
    -1.01
    amna
    -1.00
     nasıl
    -1.00
    dirond
    -0.99
    erted
    -0.98
    zaba
    -0.98
     pautas
    -0.98
    ovo
    -0.97
    POSITIVE LOGITS
     you
    1.28
     ваше
    1.18
     your
    1.17
    看不
    1.12
     Estación
    1.09
     $\&$
    1.09
     Muñoz
    1.05
    hejiang
    1.05
    VEHICLE
    1.05
    ay
    1.04
    Activations Density 0.034%

    No Known Activations