© 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. 18793
    Prev
    Next
    INDEX
    Explanations

    discover, generate, or translate

    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
     cotton
    0.46
    CB
    0.43
    Cotton
    0.42
    棉
    0.42
     overcast
    0.41
    3
    0.41
    極
    0.40
    angleOf
    0.40
    घ
    0.39
    糯
    0.39
    POSITIVE LOGITS
     notícia
    0.46
     Leistungen
    0.45
     dejó
    0.43
     systèmes
    0.43
    ್
    0.43
    
    0.43
    ပြင်
    0.42
     coalgebras
    0.42
     pasó
    0.42
    rául
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.