© 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. 34229
    Prev
    Next
    INDEX
    Explanations

    Hunting Trips

    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
     and
    -1.44
     in
    -1.36
     also
    -1.25
     tablette
    -1.21
    ppings
    -1.20
     酥
    -1.20
    
    -1.19
    hirt
    -1.18
    rary
    -1.16
    ixante
    -1.16
    POSITIVE LOGITS
    1.28
     isoliert
    1.25
     vorbere
    1.23
     begrenzt
    1.23
     behalten
    1.21
     deaktiviert
    1.21
     beeinf
    1.20
     annehmen
    1.19
     gefördert
    1.19
     berechtigt
    1.17
    Activations Density 0.003%

    No Known Activations