© 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. 143949
    Prev
    Next
    INDEX
    Explanations

    specific condition

    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
     بج
    0.47
     \%
    0.47
    ดย
    0.45
     प्रमाणित
    0.44
     ilmiah
    0.44
     bona
    0.43
    連結
    0.42
    कांनी
    0.42
     ضمن
    0.42
     Undo
    0.42
    POSITIVE LOGITS
    Refer
    0.49
    ла
    0.48
    Height
    0.47
    ת
    0.46
    ൻ
    0.45
    Rex
    0.44
    骶
    0.44
    ྟ
    0.43
    Cyber
    0.43
    Negative
    0.42
    Activations Density 0.002%

    No Known Activations