© 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-65K
    7. 353
    Prev
    Next
    INDEX
    Explanations

    the result host system core cast

    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_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
    ir
    0.90
    ra
    0.80
    ى
    0.75
    ri
    0.66
    2
    0.61
    6
    0.60
    ミ
    0.59
    li
    0.58
    4
    0.58
    ih
    0.57
    POSITIVE LOGITS
     be
    0.82
    ה
    0.70
     was
    0.68
    т
    0.67
    د
    0.67
     are
    0.66
     que
    0.61
    д
    0.61
    <0xAD>
    0.58
    고
    0.58
    Activations Density 0.422%

    No Known Activations