© 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. 66983
    Prev
    Next
    INDEX
    Explanations

    Measuring Brain, Doughboy, Q:, The Largest, Ken:

    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
     \"
    -1.16
    ..."
    -1.06
     "
    -1.05
     März
    -1.00
    ~!
    -0.97
    ...?
    -0.95
     bouquet
    -0.94
    a
    -0.92
     sexto
    -0.92
    ↵↵
    -0.91
    POSITIVE LOGITS
    嘹
    1.11
    plings
    1.11
    tocin
    1.06
    ഷ
    1.06
    }}_{\
    1.06
    вости
    1.06
    盱
    1.05
    paraíso
    1.05
     our
    1.04
    ஷ
    1.04
    Activations Density 0.000%

    No Known Activations