© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 40245
    Prev
    Next
    INDEX
    Explanations

    listing citation details

    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
    While
    -1.07
    Maybe
    -1.07
    Like
    -1.05
    ⲟ
    -1.04
    aggiare
    -1.04
    Perhaps
    -1.03
    Generally
    -1.03
    ᧐
    -1.02
     in
    -1.02
    Any
    -0.99
    POSITIVE LOGITS
     véhicules
    1.15
     crochê
    1.13
     couro
    1.11
    Hag
    1.07
     niveaux
    1.07
     tecido
    1.07
     degrés
    1.06
    textfield
    1.04
     discut
    1.02
     borracha
    1.02
    Activations Density 0.006%

    No Known Activations