© 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. 85859
    Prev
    Next
    INDEX
    Explanations

    in practice

    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
    ى
    0.63
    et
    0.61
    ası
    0.55
    rangian
    0.55
    ারের
    0.54
     ruth
    0.53
     ihrem
    0.52
    od
    0.52
     their
    0.51
     यांचा
    0.51
    POSITIVE LOGITS
    ك
    0.96
    스
    0.80
    يا
    0.79
    ה
    0.70
    ଭ
    0.67
    마
    0.67
    ✨
    0.67
    မ
    0.66
    드
    0.66
    சு
    0.66
    Activations Density 0.002%

    No Known Activations