© 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. 16-GEMMASCOPE-2-RES-262K
    7. 27358
    Prev
    Next
    INDEX
    Explanations

    flutter code

    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_16_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
     is
    0.77
    ？
    0.72
    and
    0.70
     Rapids
    0.66
    OT
    0.64
    ра
    0.63
     Freshman
    0.63
     Trad
    0.62
     Расійскай
    0.62
     on
    0.61
    POSITIVE LOGITS
    uje
    0.80
    }$;
    0.74
    ’।
    0.73
    에
    0.70
    }",
    0.70
    izada
    0.69
    anın
    0.68
    </sup>
    0.68
    ن
    0.67
    ।’
    0.66
    Activations Density 0.001%

    No Known Activations