© 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. 9446
    Prev
    Next
    INDEX
    Explanations

    casting, specifying, coding

    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
    纔
    -1.59
    $
    -1.56
    da
    -1.48
    蹀
    -1.45
     pérd
    -1.45
    IZEN
    -1.43
    }
    -1.42
    一愣
    -1.42
     vengono
    -1.41
    Venture
    -1.38
    POSITIVE LOGITS
     a
    1.89
     an
    1.63
    placer
    1.49
     for
    1.39
    蛧
    1.38
     says
    1.35
    できません
    1.34
    分からない
    1.33
     namorados
    1.32
     unusual
    1.31
    Activations Density 0.116%

    No Known Activations