© 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. 251170
    Prev
    Next
    INDEX
    Explanations

    pinterest, Mirror, new, beings, cardboard

    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
    introduced
    0.49
    낀
    0.47
    looped
    0.46
    Kana
    0.46
    maintained
    0.43
    Samsung
    0.43
    Radar
    0.43
    너
    0.43
    Brady
    0.42
    Cycles
    0.42
    POSITIVE LOGITS
    ى
    0.48
    حث
    0.48
     देखें
    0.47
     sampai
    0.47
     pm
    0.47
    ड़ी
    0.47
     hiệp
    0.46
     dan
    0.46
     loại
    0.46
    ান
    0.46
    Activations Density 0.000%

    No Known Activations