© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 1146
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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_16k_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
     ===============
    1.56
    
    1.55
     (\"
    1.53
    🈚
    1.52
    います
    1.46
    
    1.46
    इंडीज
    1.45
    itoti
    1.44
    enia
    1.44
     preclude
    1.42
    POSITIVE LOGITS
    And
    1.66
     And
    1.50
    まるで
    1.39
    WebServlet
    1.36
    В
    1.34
    qe
    1.31
     पूछता
    1.29
    k
    1.29
    將
    1.28
     bref
    1.27
    Activations Density 0.197%

    No Known Activations