© 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. 17612
    Prev
    Next
    INDEX
    Explanations

    snap photos and sudden actions

    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
     miRNAs
    1.17
     `:`
    1.00
    Ι
    1.00
    وق
    1.00
    ib
    0.99
    Từ
    0.98
    ކ
    0.96
    ﺍ
    0.96
    ون
    0.96
    т
    0.96
    POSITIVE LOGITS
     can
    1.25
     snap
    1.18
     snapped
    1.09
     are
    1.07
     denial
    1.02
     be
    1.00
    ↵↵
    0.99
     dua
    0.97
     zing
    0.97
     user
    0.95
    Activations Density 0.008%

    No Known Activations