© 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. 46416
    Prev
    Next
    INDEX
    Explanations

    junit.test

    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
    اي
    0.72
    ні
    0.68
    en
    0.66
    اً
    0.64
    ↵↵
    0.62
    ных
    0.62
    our
    0.61
    of
    0.61
    ಾ
    0.60
    از
    0.59
    POSITIVE LOGITS
    tch
    0.80
    kD
    0.72
    c
    0.64
    К
    0.63
    Լ
    0.63
    ন্তু
    0.63
    Ե
    0.63
    ஷன்
    0.62
    他不
    0.62
    פה
    0.61
    Activations Density 0.000%

    No Known Activations