© 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. 29779
    Prev
    Next
    INDEX
    Explanations

    Explaining historical mysteries and origins

    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
    最具
    0.49
    ਤੀ
    0.48
    雰
    0.44
    ային
    0.44
    全民
    0.42
    Investor
    0.42
    권
    0.42
    ذ
    0.42
     ROY
    0.41
    合物
    0.41
    POSITIVE LOGITS
    ao
    0.51
     years
    0.46
    era
    0.46
     et
    0.45
     hooked
    0.44
    aa
    0.44
     prolong
    0.44
     suffering
    0.44
    do
    0.43
    hook
    0.43
    Activations Density 0.005%

    No Known Activations