© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 183939
    Prev
    Next
    INDEX
    Explanations

    explaining strategy and impact

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

    Control Flow

    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
    dU
    0.48
    >*
    0.46
    цкий
    0.45
    führer
    0.45
     வேண்ட
    0.42
    BrI
    0.42
    y
    0.41
     igualdad
    0.41
     جميلة
    0.41
    emples
    0.40
    POSITIVE LOGITS
    ၷ
    0.50
    साइ
    0.49
     Lis
    0.47
     Nagano
    0.47
     Lyn
    0.47
     warrants
    0.45
    Всім
    0.45
     anticipated
    0.45
    빡
    0.45
     deline
    0.45
    Activations Density 0.001%

    No Known Activations