© 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. 227298
    Prev
    Next
    INDEX
    Explanations

    darkest tragedy

    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
     Dahmer
    0.55
    厂
    0.53
    暑
    0.52
     Neues
    0.48
    دو
    0.47
    喇
    0.46
    岸
    0.46
    姒
    0.46
    ,’
    0.46
     Punkt
    0.45
    POSITIVE LOGITS
     perd
    0.50
     является
    0.48
    perd
    0.48
     フロント
    0.47
     clandestine
    0.45
    не
    0.44
     प्रतिमा
    0.43
     ی
    0.42
     тво
    0.42
     exemplifies
    0.42
    Activations Density 0.000%

    No Known Activations