© 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. 53347
    Prev
    Next
    INDEX
    Explanations

    dual use or features

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

    dual nature and duality

    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
    ur
    0.86
    ul
    0.72
    ي
    0.72
    un
    0.71
    el
    0.70
    其他
    0.70
    it
    0.64
    i
    0.64
    ið
    0.63
    a
    0.63
    POSITIVE LOGITS
     dual
    0.89
     Dual
    0.85
    Dual
    0.84
     dwóch
    0.78
     duality
    0.75
     dichotom
    0.74
     双
    0.70
     दोन
    0.67
    的双
    0.66
     две
    0.64
    Activations Density 0.083%

    No Known Activations