© 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. 31-GEMMASCOPE-2-RES-262K
    7. 16994
    Prev
    Next
    INDEX
    Explanations

    breakdown of lists

    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
    C
    0.46
    H
    0.44
    W
    0.44
     Summer
    0.44
    G
    0.44
    Summer
    0.41
    U
    0.41
    M
    0.40
    A
    0.40
    '
    0.39
    POSITIVE LOGITS
     しかし
    0.37
     pebbles
    0.36
    這樣子
    0.36
     pyaar
    0.35
    じた
    0.34
     critters
    0.33
     existentes
    0.33
     percol
    0.33
     التي
    0.32
     shenanigans
    0.32
    Activations Density 0.163%

    No Known Activations