© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 2276
    Prev
    Next
    INDEX
    Explanations

    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-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    x
    0.56
     into
    0.54
     push
    0.54
    apple
    0.54
     apple
    0.54
     fleet
    0.53
    l
    0.52
    .
    0.51
     in
    0.51
     sheep
    0.51
    POSITIVE LOGITS
     తన
    0.55
    êmio
    0.54
     защото
    0.50
     призна
    0.49
     повин
    0.49
     geomét
    0.49
     డే
    0.48
     தயாரி
    0.48
     кантора
    0.47
    囫
    0.47
    Activations Density 0.000%

    No Known Activations