© 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. 3793
    Prev
    Next
    INDEX
    Explanations

    mm for

    np_acts-logits-general · gemini-2.5-flash-lite

    descriptive constructions about a person’s characteristic mannerisms or behaviors, typically phrased as “the way [subject] …” statements.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    で
    0.37
     ciel
    0.35
     ලි
    0.35
     سط
    0.34
     மற்ற
    0.34
    ים
    0.34
    辩
    0.34
    म्
    0.33
     بر
    0.33
     mantras
    0.33
    POSITIVE LOGITS
    illegal
    0.38
    হতের
    0.37
     किंतु
    0.37
    ிகளுக்கு
    0.36
    jail
    0.36
    ian
    0.34
     Appeal
    0.34
    लेकिन
    0.34
    जेक्शन
    0.34
    但这
    0.33
    Activations Density 0.186%

    No Known Activations