© 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. 33886
    Prev
    Next
    INDEX
    Explanations

    TABLE

    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
    ӓ
    -1.20
     occafion
    -1.11
     صندوق
    -1.05
     Já
    -1.05
    "],
    -1.05
     dévou
    -1.02
    歺
    -1.02
     overridden
    -1.02
    ujem
    -1.02
    verns
    -1.02
    POSITIVE LOGITS
     you
    1.16
     what
    1.01
    car
    0.97
     car
    0.97
     into
    0.95
     health
    0.94
    R
    0.94
     
    0.94
     t
    0.94
     You
    0.93
    Activations Density 0.001%

    No Known Activations