© 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. 26751
    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
     after
    -2.19
     if
    -2.13
     from
    -2.08
     in
    -2.05
     give
    -1.94
     had
    -1.92
     gets
    -1.91
     by
    -1.89
     what
    -1.84
     supremely
    -1.82
    POSITIVE LOGITS
    沵
    1.91
     jezt
    1.91
     decidedly
    1.82
    𨨏
    1.79
    킁
    1.79
     magnificent
    1.77
    腚
    1.77
     sooo
    1.75
    (>
    1.75
     delightfully
    1.74
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.