© 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. 1463
    Prev
    Next
    INDEX
    Explanations

    subjects, limits, generation, caching, targets

    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
     are
    0.61
    માં
    0.60
    ی
    0.54
    ק
    0.54
    ان
    0.53
    ك
    0.52
    ين
    0.51
     has
    0.50
    ل
    0.50
    ون
    0.49
    POSITIVE LOGITS
    ०
    0.46
    pe
    0.40
    ulation
    0.40
    mo
    0.39
    ۰
    0.38
    iril
    0.37
    pu
    0.33
    ologne
    0.32
    U
    0.32
    ella
    0.31
    Activations Density 1.043%

    No Known Activations