Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-65K
    4. 46851
    Prev
    Next
    INDEX
    Explanations

    Linux Enterprise Server

    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_65k_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
     peroxide
    1.38
     photochemical
    1.37
    РЕ
    1.37
    पूर्व
    1.35
    𝟬
    1.35
    История
    1.34
    Нет
    1.33
    Фе
    1.33
    И
    1.30
    િસ
    1.30
    POSITIVE LOGITS
    ivatives
    1.07
    வற்றை
    0.97
     справ
    0.93
    𝑑
    0.91
     απαι
    0.89
    ability
    0.86
    pared
    0.86
    bodies
    0.85
    ত্বের
    0.84
    
    0.83
    Activations Density 0.002%

    No Known Activations