© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 2276
    Prev
    Next
    INDEX
    Explanations

    foreign language words

    np_acts-logits-general · gemini-2.5-flash-lite

    how to implement CLI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     into
    0.52
     fleet
    0.52
    apple
    0.52
     apple
    0.52
     orange
    0.49
    fleet
    0.49
     sheep
    0.49
    x
    0.48
     push
    0.48
     strikes
    0.48
    POSITIVE LOGITS
    êmio
    0.55
     తన
    0.54
     повин
    0.52
     தயாரி
    0.51
     నాగ
    0.50
     geomét
    0.50
     кур
    0.49
     защото
    0.49
     επίσης
    0.49
     верно
    0.48
    Activations Density 0.000%

    No Known Activations