© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 161200
    Prev
    Next
    INDEX
    Explanations

    mentioning quantity or specific items

    np_acts-logits-general · gemini-2.5-flash-lite

    realistic, bottleneck, foundational concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dad
    0.42
    Abroad
    0.40
    漑
    0.39
     હતા
    0.39
     продви
    0.38
     clipart
    0.38
     ይችላል
    0.37
    
    0.37
     görün
    0.36
     Ingles
    0.36
    POSITIVE LOGITS
     Są
    0.43
    9
    0.43
     offres
    0.42
     tỷ
    0.41
    arze
    0.40
     Typed
    0.40
     Jy
    0.40
    MeV
    0.40
     falleció
    0.40
    oung
    0.39
    Activations Density 0.000%

    No Known Activations