© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11132
    Prev
    Next
    INDEX
    Explanations

    invention or technical descriptions

    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
    nadier
    -1.12
     galeria
    -1.11
    ṁ
    -1.09
    ṅ
    -1.05
    Cartney
    -1.02
     capot
    -1.01
     strategie
    -0.97
    gregor
    -0.95
     cintur
    -0.95
     个
    -0.95
    POSITIVE LOGITS
     navigazione
    1.13
    Allora
    1.11
     that
    1.09
     sentito
    1.07
     piattaforma
    1.05
     chiese
    1.04
     spagnolo
    1.03
     servido
    1.02
     беременности
    1.02
     trasmissione
    1.00
    Activations Density 0.000%

    No Known Activations