© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 120426
    Prev
    Next
    INDEX
    Explanations

    interference and interferometry

    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
    ма
    0.83
    يم
    0.74
    كان
    0.72
    <unused46>
    0.61
    قية
    0.60
    auff
    0.60
    اليه
    0.59
    കൊ
    0.59
    мани
    0.59
    قيم
    0.57
    POSITIVE LOGITS
    -
    0.92
    v
    0.77
    a
    0.75
    w
    0.74
     dioxide
    0.71
     hinged
    0.68
     rupee
    0.68
    y
    0.68
     yummy
    0.67
     waxaa
    0.67
    Activations Density 0.001%

    No Known Activations