© 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. 11426
    Prev
    Next
    INDEX
    Explanations

    ICF construction or ED glass

    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
    گاه
    1.12
    thorne
    1.09
    حر
    1.08
    hetamine
    1.05
    idation
    1.05
     poster
    1.02
     bookings
    1.02
    
    1.02
    arakhand
    1.00
     Really
    1.00
    POSITIVE LOGITS
    𝑤
    1.27
    m
    1.24
    n
    1.23
     രീതി
    1.23
     వాహ
    1.21
    lə
    1.19
    sav
    1.13
     engag
    1.13
    cInfo
    1.12
     schn
    1.10
    Activations Density 0.000%

    No Known Activations