© 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. 10-GEMMASCOPE-RES-131K
    4. 42815
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    providedIn
    -2.20
    Sebagai
    -2.19
     rafra
    -2.16
    Beberapa
    -2.16
    Setiap
    -2.13
     éc
    -2.08
     blusa
    -2.06
     brosse
    -2.06
    Sementara
    -2.05
    Gleich
    -2.05
    POSITIVE LOGITS
     that
    2.39
     and
    2.30
     when
    2.19
     of
    2.19
     or
    2.17
     which
    1.95
     they
    1.93
     where
    1.88
     in
    1.79
     at
    1.77
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.