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. 1783
    Prev
    Next
    INDEX
    Explanations

    section headings

    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
     crowning
    1.33
    एं
    1.31
    Также
    1.30
    IPS
    1.30
    झा
    1.30
    Interestingly
    1.30
    儡
    1.29
     relatively
    1.29
    وما
    1.28
    ****************
    1.27
    POSITIVE LOGITS
    ০
    1.72
    ০১
    1.64
    
    1.53
    েও
    1.53
    ו
    1.52
    ность
    1.45
    ে
    1.42
    ك
    1.35
     obce
    1.34
    től
    1.34
    Activations Density 0.001%

    No Known Activations