© 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. 10-GEMMASCOPE-RES-131K
    7. 99001
    Prev
    Next
    INDEX
    Explanations

    database queries and results

    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_10/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
    ± 
    -1.36
     such
    -1.23
    </h2>
    -1.20
     like
    -1.14
    런
    -1.13
     similares
    -1.12
     durfte
    -1.12
     éves
    -1.10
    .”
    -1.09
     Prozent
    -1.09
    POSITIVE LOGITS
    .
    1.27
     "
    1.22
    winner
    1.17
     JY
    1.16
    ？』
    1.16
    我が家の
    1.14
    tyimages
    1.13
    결
    1.13
    <0xE0>
    1.13
    isling
    1.12
    Activations Density 0.039%

    No Known Activations