© 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. 22-GEMMASCOPE-2-RES-262K
    7. 19312
    Prev
    Next
    INDEX
    Explanations

    wind phenomena

    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_22_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
     conjunction
    0.96
    arthritis
    0.96
    ++++
    0.92
     arsenic
    0.92
    ണ്ണം
    0.91
     ground
    0.90
     $(<
    0.88
    itiv
    0.87
     distal
    0.86
     wedding
    0.85
    POSITIVE LOGITS
    blown
    1.79
    surfing
    1.46
     blowing
    1.42
     gusts
    1.42
     Blowing
    1.19
    breakers
    1.17
    筝
    1.16
     blown
    1.16
    箏
    1.14
     blew
    1.13
    Activations Density 0.021%

    No Known Activations