© 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. 128880
    Prev
    Next
    INDEX
    Explanations

    fruct, BH, cuz, virtue

    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
    𐐪
    -3.05
    鲣
    -2.98
    炱
    -2.92
    渽
    -2.91
    涐
    -2.89
    蒌
    -2.86
    歛
    -2.83
     fön
    -2.83
    檍
    -2.83
    銪
    -2.78
    POSITIVE LOGITS
    '
    4.25
     
    3.52
    ",
    3.44
     I
    3.42
     It
    3.11
    n
    3.05
    --
    2.97
    …
    2.97
    不管是
    2.94
    A
    2.92
    Activations Density 0.008%

    No Known Activations