© 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. 74406
    Prev
    Next
    INDEX
    Explanations

    names and roles

    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
    ドール
    -1.23
    の概要
    -1.20
     réglementation
    -1.16
    ドット
    -1.11
    購買
    -1.11
    ボトル
    -1.10
    を活用
    -1.09
     усі
    -1.09
     majorité
    -1.06
     évaluation
    -1.06
    POSITIVE LOGITS
     színes
    1.47
     µ
    1.37
    SetColor
    1.35
     cerveja
    1.34
     simplemente
    1.34
    enschutz
    1.33
    ꩜
    1.32
     białe
    1.31
    colhead
    1.31
    utup
    1.31
    Activations Density 0.001%

    No Known Activations