© 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-262K
    7. 10926
    Prev
    Next
    INDEX
    Explanations

    system programming headers

    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
    g
    1.62
    و
    1.53
    k
    1.52
    aan
    1.52
    kt
    1.49
    ي
    1.45
    et
    1.40
    ra
    1.38
    de
    1.36
    yon
    1.35
    POSITIVE LOGITS
    \{-\
    1.59
     moieties
    1.55
     punishments
    1.50
     refinements
    1.48
     isoforms
    1.48
     smoothies
    1.47
     restrooms
    1.47
     Strath
    1.45
     mergers
    1.41
    
    1.39
    Activations Density 0.001%

    No Known Activations