© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38349
    Prev
    Next
    INDEX
    Explanations

    url paths and file extensions

    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
     in
    -2.06
     or
    -2.05
     this
    -1.94
     that
    -1.86
     after
    -1.84
     before
    -1.82
     an
    -1.81
     After
    -1.78
     on
    -1.73
     at
    -1.70
    POSITIVE LOGITS
     faciliter
    1.73
    Kleur
    1.68
    Postup
    1.66
    ܆
    1.66
     sélectionner
    1.63
    Kdo
    1.59
     obtenir
    1.58
     éviter
    1.57
    Kde
    1.56
    Prijs
    1.55
    Activations Density 0.019%

    No Known Activations