© 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. 10-GEMMASCOPE-RES-131K
    7. 111778
    Prev
    Next
    INDEX
    Explanations

    sparse information or data

    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_10/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
    蛱
    -2.08
    ?”
    -1.99
    渽
    -1.95
    讥
    -1.95
     Ambos
    -1.91
    ⒈
    -1.88
    🍶
    -1.86
    鸸
    -1.86
    塍
    -1.84
    擽
    -1.83
    POSITIVE LOGITS
    ="
    2.02
    \
    2.02
    where
    2.02
    which
    1.97
    et
    1.95
    e
    1.91
    8
    1.89
    礻
    1.86
    3
    1.86
    x
    1.84
    Activations Density 0.024%

    No Known Activations