© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129501
    Prev
    Next
    INDEX
    Explanations

    visit this page

    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
    个月
    -0.94
    naire
    -0.93
    </em>
    -0.91
    老板
    -0.91
     hinten
    -0.90
    ¬
    -0.90
     противополо
    -0.90
    예
    -0.89
    )
    -0.89
    ub
    -0.89
    POSITIVE LOGITS
     with
    1.13
     visited
    1.07
    usata
    1.05
     interessantes
    1.03
    岌
    1.02
     visit
    0.99
     at
    0.99
    НИЕ
    0.99
     during
    0.98
    ganta
    0.97
    Activations Density 0.038%

    No Known Activations