© 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. 39703
    Prev
    Next
    INDEX
    Explanations

    no result or failure

    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
     zanahoria
    -1.16
     vinaigre
    -1.16
     brinquedos
    -1.05
    commodations
    -1.03
     naviguant
    -1.02
     soigne
    -1.01
     دیگران
    -1.01
    ğraf
    -1.01
     vainilla
    -1.00
    scoring
    -1.00
    POSITIVE LOGITS
     first
    1.13
    No
    1.13
    RE
    1.11
    More
    1.08
     not
    1.05
    <>
    1.04
    ΡΟ
    1.01
     rekomendasi
    0.98
    IN
    0.97
     only
    0.96
    Activations Density 0.139%

    No Known Activations