© 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. 7224
    Prev
    Next
    INDEX
    Explanations

    aboard a ship

    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
    ⬈
    -2.64
    приклад
    -2.11
     energía
    -2.09
    逦
    -2.06
     животные
    -2.05
    龊
    -2.03
    摇了
    -2.02
    ☫
    -2.02
     儿
    -1.99
    瑗
    -1.99
    POSITIVE LOGITS
    ﮦ
    2.63
    0
    2.41
    ㈬
    2.38
    genodigd
    2.36
    This
    2.33
    By
    2.31
     برای
    2.30
    Unfortunately
    2.30
    豋
    2.25
    Interestingly
    2.23
    Activations Density 0.001%

    No Known Activations