© 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. 8519
    Prev
    Next
    INDEX
    Explanations

    anthropology and related academic fields

    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
    ка
    1.48
    s
    1.47
    та
    1.41
    ك
    1.29
    ح
    1.12
    ع
    1.09
    س
    1.02
    ри
    1.01
    on
    0.98
    suc
    0.98
    POSITIVE LOGITS
    ’
    1.13
    ;
    1.07
     Anthropology
    0.96
    :
    0.95
    ić
    0.90
     anthrop
    0.89
     anthropologists
    0.89
     for
    0.88
     anthropology
    0.85
     boxe
    0.85
    Activations Density 0.001%

    No Known Activations