© 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-65K
    7. 5949
    Prev
    Next
    INDEX
    Explanations

    categories and descriptions

    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_65k_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
    ⨔
    0.35
     తగ్
    0.35
    ทั้ง
    0.35
    คง
    0.34
    The
    0.34
     للم
    0.33
    ));
    0.33
     বিদ্যালয়ের
    0.33
     Selasa
    0.33
    ด
    0.33
    POSITIVE LOGITS
    that
    0.66
     which
    0.64
     that
    0.61
     الذي
    0.55
     που
    0.52
    which
    0.51
    ian
    0.48
     whose
    0.47
    ia
    0.46
     we
    0.45
    Activations Density 0.130%

    No Known Activations