© 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. 84326
    Prev
    Next
    INDEX
    Explanations

    Wheel of the Year

    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
    haviours
    -1.51
    茈
    -1.48
     zyn
    -1.47
     integri
    -1.45
     oogen
    -1.42
     LIABLE
    -1.38
    탉
    -1.38
     ***!
    -1.35
     qualsiasi
    -1.34
    垻
    -1.30
    POSITIVE LOGITS
     and
    1.63
    ↵
    1.53
    :
    1.49
     &
    1.41
     all
    1.41
     обычно
    1.30
     ночью
    1.27
    <b>
    1.21
    鉅
    1.20
     otras
    1.18
    Activations Density 0.020%

    No Known Activations