© 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. 115316
    Prev
    Next
    INDEX
    Explanations

    conférences and organizations

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

    often, usually, depends

    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
    یمپ
    0.48
    فاق
    0.47
    임을
    0.47
    神
    0.47
    came
    0.46
    佛
    0.45
    絡
    0.45
    பி
    0.44
    手の
    0.44
    受注
    0.44
    POSITIVE LOGITS
    </blockquote>
    0.49
     कथित
    0.46
     Estimates
    0.46
     अंतरिक्ष
    0.46
     conférence
    0.45
     "
    0.44
     মুঠ
    0.44
     prettier
    0.44
     संवैधानिक
    0.44
     \%
    0.43
    Activations Density 0.001%

    No Known Activations