© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10034
    Prev
    Next
    INDEX
    Explanations

    units of measure and pumping

    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
    য়ের
    3.15
    য়ের
    3.14
     ramas
    2.88
     ​​
    2.71
    که
    2.69
    
    2.69
    schild
    2.53
    tedir
    2.50
     víctimas
    2.48
    ları
    2.48
    POSITIVE LOGITS
    ي
    5.28
    м
    4.69
    in
    4.36
    ა
    4.35
    ل
    4.35
    क
    4.32
    en
    4.18
    i
    4.09
    ি
    4.07
    ার
    3.89
    Activations Density 0.168%

    No Known Activations