© 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. 38999
    Prev
    Next
    INDEX
    Explanations

    exchange or redeem

    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
    𓋼
    -1.32
    ೢ
    -1.17
     samme
    -1.15
    verse
    -1.14
     same
    -1.14
    脔
    -1.14
     mesmos
    -1.12
     ajoute
    -1.12
    folge
    -1.09
    still
    -1.09
    POSITIVE LOGITS
     on
    1.57
    หน้านี้
    1.38
    État
    1.26
    曄
    1.15
     утром
    1.14
    വ
    1.12
     січня
    1.09
    apest
    1.09
    他们
    1.08
    Sinon
    1.08
    Activations Density 0.033%

    No Known Activations