© 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. 39899
    Prev
    Next
    INDEX
    Explanations

    operations, profit, proliferation, countries

    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
    ؟!
    0.48
     ؟
    0.44
     গলায়
    0.42
     разделить
    0.41
     Corning
    0.41
    ؟
    0.40
     модерни
    0.40
    이블
    0.39
     יי
    0.39
    кор
    0.39
    POSITIVE LOGITS
     your
    0.42
     when
    0.42
     wọn
    0.41
     Financial
    0.40
     someone
    0.40
    ὢ
    0.38
     it
    0.38
    Alias
    0.38
    mixin
    0.38
    cadilly
    0.38
    Activations Density 0.001%

    No Known Activations