© 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. 100158
    Prev
    Next
    INDEX
    Explanations

    Culture Fit, beliefs regarding

    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
    ږئ
    0.52
    на
    0.49
    ὺ
    0.47
     نه
    0.46
    ろ
    0.45
     první
    0.45
    屻
    0.45
    價
    0.44
    й
    0.44
     Großbritannien
    0.44
    POSITIVE LOGITS
     (
    0.56
     with
    0.52
     that
    0.49
    จะไม่
    0.49
    <
    0.49
     upsetting
    0.47
    ->
    0.46
     exception
    0.46
    :<
    0.46
    itan
    0.45
    Activations Density 0.000%

    No Known Activations