© 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. 25277
    Prev
    Next
    INDEX
    Explanations

    package 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
    CharStream
    -1.21
    uated
    -1.16
    ANNEL
    -1.16
     nowy
    -1.15
     schlaf
    -1.14
     extranjeros
    -1.13
    idopsis
    -1.12
    rento
    -1.09
     mixture
    -1.09
    eſ
    -1.09
    POSITIVE LOGITS
     when
    1.26
    スポンサーリンク
    1.20
    ないです
    1.07
     that
    1.05
    ハンドメイド
    1.03
     breeches
    1.02
    ámos
    1.02
    </b>
    1.00
    华丽
    1.00
     However
    0.99
    Activations Density 0.060%

    No Known Activations