© 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. 128961
    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
    -2.16
     all
    -2.02
     with
    -1.91
     on
    -1.87
     so
    -1.86
     every
    -1.84
     get
    -1.77
     had
    -1.73
     by
    -1.70
     this
    -1.70
    POSITIVE LOGITS
    都已经
    1.77
     MATTERS
    1.69
    下意识
    1.62
    这般
    1.61
     accentu
    1.59
    ,;
    1.55
     forestal
    1.53
     exasperated
    1.53
     devast
    1.52
     THOUS
    1.52
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.