© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34260
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     their
    -1.90
     what
    -1.55
     both
    -1.40
     more
    -1.39
     for
    -1.36
     without
    -1.34
     almost
    -1.23
     most
    -1.21
     people
    -1.20
     some
    -1.16
    POSITIVE LOGITS
    Preparazione
    1.30
     propo
    1.27
     dadurch
    1.23
    取决
    1.19
     EIGHT
    1.19
    Descriere
    1.16
    بسم
    1.12
     COULD
    1.09
     REMEMBER
    1.09
     OUTSIDE
    1.08
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.