© 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. 14852
    Prev
    Next
    INDEX
    Explanations

    fire followed by fly, walls, fighter, stone

    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
     bled
    1.00
    ا
    0.97
     wied
    0.89
     humorous
    0.89
    Па
    0.89
    셈
    0.88
     Ми
    0.87
     metri
    0.87
    йс
    0.86
     zel
    0.86
    POSITIVE LOGITS
     extinguishers
    1.67
    nze
    1.63
    🔥🔥
    1.61
    crackers
    1.57
     extinguisher
    1.52
    fighters
    1.48
    cracker
    1.44
     hydrant
    1.30
    प्लेस
    1.29
    flies
    1.26
    Activations Density 0.033%

    No Known Activations