© 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. 245440
    Prev
    Next
    INDEX
    Explanations

    political testimony or regulation

    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
     enn
    0.48
    襯
    0.47
    經常
    0.46
     desafios
    0.46
     défis
    0.45
     mutter
    0.45
     silencio
    0.45
     dichloromethane
    0.45
     CHALL
    0.45
     audiovis
    0.44
    POSITIVE LOGITS
    Burg
    0.52
    Angleterre
    0.47
    🏠
    0.45
    Away
    0.43
    ക്കുകയും
    0.43
    有两个
    0.43
    ટ્સ
    0.42
    🏥
    0.42
    Accordingly
    0.42
    给定
    0.42
    Activations Density 0.003%

    No Known Activations