© 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. 11491
    Prev
    Next
    INDEX
    Explanations

    Lettuce, German, LLC, Egypt

    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
    sning
    1.57
    ים
    1.38
    Ϫ
    1.35
    নন্দ
    1.34
    ляем
    1.33
     leren
    1.30
    ycin
    1.30
    ━━━━
    1.30
    mith
    1.29
    ektor
    1.26
    POSITIVE LOGITS
    ionati
    1.53
    çük
    1.42
    withstanding
    1.29
    autical
    1.28
     NoSuch
    1.28
    𝟘
    1.28
    ographed
    1.27
    พันธุ์
    1.26
     další
    1.25
    л
    1.25
    Activations Density 0.000%

    No Known Activations