© 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. 16131
    Prev
    Next
    INDEX
    Explanations

    statements, gender, sixth, you, 1, at

    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
    一趟
    -0.95
     regra
    -0.93
    一只
    -0.92
     intric
    -0.90
    ^(-
    -0.88
     disponib
    -0.87
    ativität
    -0.86
     Focused
    -0.85
     Initi
    -0.84
    KommentareTeilen
    -0.84
    POSITIVE LOGITS
     about
    1.40
     vanno
    1.09
     may
    1.04
     which
    1.01
    predictions
    0.99
     based
    0.99
    اريخ
    0.96
     our
    0.94
     usually
    0.94
    setDisabled
    0.90
    Activations Density 0.006%

    No Known Activations