© 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
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 10572
    Prev
    Next
    INDEX
    Explanations

    fibrin, clot, anaphylaxis, bivariate, hyperconjugation

    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
    і
    2.89
    יות
    2.76
    et
    2.49
    बाजी
    2.37
    साइटी
    2.34
    ти
    2.33
    ي
    2.26
    σουμε
    2.16
    esque
    2.15
     ouvertes
    2.15
    POSITIVE LOGITS
    inology
    2.61
    tı
    2.42
    iseconds
    2.41
    ן
    2.41
    cando
    2.39
    
    2.30
     malloc
    2.29
    treme
    2.29
     benda
    2.25
    ции
    2.24
    Activations Density 0.015%

    No Known Activations