© 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. 15380
    Prev
    Next
    INDEX
    Explanations

    exit codes 0 or 1

    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
     perumahan
    -1.12
     of
    -1.09
     cartaz
    -1.02
     daudz
    -1.02
     laikā
    -1.02
     ícone
    -1.02
     valamint
    -1.02
     silang
    -1.00
     bēr
    -1.00
    :|
    -0.99
    POSITIVE LOGITS
     необходимости
    1.20
     textAlign
    1.16
    三個
    1.15
     maxHeight
    1.15
    外部連結
    1.14
    潜力
    1.14
    怎么回事
    1.12
     einander
    1.12
    そこで
    1.08
    機器
    1.08
    Activations Density 0.001%

    No Known Activations