© 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. 86694
    Prev
    Next
    INDEX
    Explanations

    reticulated, reticulum, luteinizing

    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
    en
    0.95
    ra
    0.92
    e
    0.90
    r
    0.83
    p
    0.82
     (
    0.81
    s
    0.78
    em
    0.77
    ut
    0.76
    im
    0.75
    POSITIVE LOGITS
     It
    0.70
    ೋಪ
    0.66
    应对
    0.63
    兢
    0.63
    પો
    0.61
    北京
    0.60
    全球
    0.60
    䨪
    0.60
    说
    0.59
     constraining
    0.59
    Activations Density 0.001%

    No Known Activations