© 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. 10-GEMMASCOPE-RES-131K
    7. 7487
    Prev
    Next
    INDEX
    Explanations

    extend followed by direction

    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
    }$
    -3.45
    횃
    -2.86
     пройдет
    -2.47
    腠
    -2.39
    埽
    -2.39
    廰
    -2.36
    鷙
    -2.36
    ೣ
    -2.34
    能源
    -2.33
    秾
    -2.33
    POSITIVE LOGITS
    </em>
    3.55
    1
    3.38
    ’
    2.95
    ↵
    2.92
    ～～
    2.66
    “
    2.56
     zahlreiche
    2.53
     amiable
    2.52
     \\
    2.48
    摃
    2.48
    Activations Density 0.029%

    No Known Activations