© 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. 45325
    Prev
    Next
    INDEX
    Explanations

    return self or this

    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
    ሖ
    -1.30
    หรือ
    -1.21
    ством
    -1.21
     one
    -1.20
    zionato
    -1.19
     员
    -1.19
     ارسال
    -1.17
     usando
    -1.16
    ти
    -1.14
     mereka
    -1.14
    POSITIVE LOGITS
     genellikle
    1.48
     that
    1.35
     imóvel
    1.33
    思議
    1.27
     always
    1.26
     メニュー
    1.25
     território
    1.24
    喟
    1.24
     being
    1.23
    関する
    1.21
    Activations Density 0.011%

    No Known Activations