© 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. 128914
    Prev
    Next
    INDEX
    Explanations

    quantifiable minimums

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    在我们
    -1.19
    Források
    -1.13
    ácii
    -1.05
    tehen
    -1.02
    Improve
    -0.97
    kiksi
    -0.97
    当我
    -0.96
     merchan
    -0.94
    想必
    -0.93
    accessoires
    -0.91
    POSITIVE LOGITS
     on
    1.02
     perhaps
    0.99
     dolorosa
    0.96
     will
    0.96
     in
    0.90
     fà
    0.89
     mola
    0.86
     unfortunately
    0.86
     those
    0.85
     of
    0.85
    Activations Density 0.057%

    No Known Activations