© 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. 9-GEMMASCOPE-2-RES-262K
    7. 8354
    Prev
    Next
    INDEX
    Explanations

    clothing and accessories

    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_9_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
    ल
    1.13
     Oven
    0.91
     sebagainya
    0.90
    לח
    0.85
    нэ
    0.84
    蛳
    0.84
    cherichia
    0.83
    喹
    0.83
    ת
    0.83
    ктери
    0.81
    POSITIVE LOGITS
     dagger
    0.93
    𝐢
    0.92
    💅
    0.90
     floral
    0.87
    💖
    0.87
    设计
    0.86
     florals
    0.86
     principales
    0.85
     corvette
    0.84
     ❤️
    0.84
    Activations Density 0.127%

    No Known Activations