© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 10549
    Prev
    Next
    INDEX
    Explanations

    visual cuts and montages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_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
    biggr
    0.72
    ά
    0.69
    brace
    0.69
    بت
    0.69
    푼
    0.69
    Per
    0.69
    朋友
    0.69
    有
    0.67
    Friend
    0.67
     friends
    0.67
    POSITIVE LOGITS
     flashbacks
    1.10
     glimpses
    1.09
     snapshots
    1.08
     flashback
    1.00
     footage
    0.97
     экране
    0.95
    footage
    0.93
     layar
    0.93
     montage
    0.91
     hindsight
    0.90
    Activations Density 0.102%

    No Known Activations