© 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. 187746
    Prev
    Next
    INDEX
    Explanations

    due diligence property owned

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

    detailed disclaimer

    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
    ために
    0.49
    يده
    0.48
     cálculo
    0.47
     gehörte
    0.45
     aproximativ
    0.45
    かね
    0.44
    어
    0.44
    च्चय
    0.42
    戸
    0.42
    лянчук
    0.42
    POSITIVE LOGITS
     तलैया
    0.55
     ঊর্ধ্ব
    0.54
    lant
    0.49
    Scorch
    0.48
     รี
    0.48
     mutilated
    0.48
     पुल्लिंग
    0.47
     aug
    0.47
     munch
    0.47
    aginaw
    0.47
    Activations Density 0.000%

    No Known Activations