© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 13649
    Prev
    Next
    INDEX
    Explanations

    lists or points

    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_40_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
    modular
    0.44
    theoretic
    0.43
    தமிழ்
    0.41
     drie
    0.40
    ﻐ
    0.40
    تباط
    0.39
    blockSize
    0.39
    ួត
    0.39
    sharp
    0.38
    docker
    0.37
    POSITIVE LOGITS
    .;
    0.69
     unless
    0.60
    ;.
    0.57
     everytime
    0.56
    .!
    0.56
     BECAUSE
    0.56
    ;
    0.54
     WHILE
    0.54
     whilst
    0.53
     INCLUDING
    0.53
    Activations Density 0.042%

    No Known Activations