© 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. 41991
    Prev
    Next
    INDEX
    Explanations

    communication and understanding

    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
     ಉಪಯೋಗ
    0.51
    minutes
    0.50
    କ୍
    0.46
    ouncil
    0.46
     WHICH
    0.44
    ERCISE
    0.44
    ‵
    0.43
    month
    0.43
    ❑
    0.43
     संपत्ति
    0.42
    POSITIVE LOGITS
    ற்றி
    0.48
     persever
    0.46
     Schrö
    0.42
    ěla
    0.42
    ită
    0.41
     Multicolor
    0.41
     thriving
    0.40
     Battles
    0.40
    ärer
    0.40
    徘
    0.40
    Activations Density 0.003%

    No Known Activations