© 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. 45223
    Prev
    Next
    INDEX
    Explanations

    content origin or attribution

    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
     it
    -1.34
    躥
    -1.34
     verknüp
    -1.33
     “
    -1.29
    蹓
    -1.23
     relacionadas
    -1.19
    儅
    -1.17
     wenige
    -1.15
    ハロウィン
    -1.15
     what
    -1.14
    POSITIVE LOGITS
     innymi
    1.58
    ଃ
    1.56
     our
    1.47
     outras
    1.47
     naše
    1.45
     unsere
    1.44
     unserer
    1.40
     otras
    1.39
    ꪔ
    1.38
     unserem
    1.38
    Activations Density 0.108%

    No Known Activations