© 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. 84176
    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
     in
    -1.27
     they
    -1.21
    ・・・・・・・・
    -1.20
    Using
    -1.16
     from
    -1.15
    When
    -1.14
    علم
    -1.14
    میر
    -1.13
     februari
    -1.12
    際に
    -1.11
    POSITIVE LOGITS
    があり
    1.48
    upported
    1.20
     Dinas
    1.20
     monstrous
    1.20
    ativeness
    1.19
    truct
    1.19
    があります
    1.19
     gesetzt
    1.18
     definiciones
    1.17
     sumptuous
    1.16
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.