© 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. 58459
    Prev
    Next
    INDEX
    Explanations

    phrase or clause continuation

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

    pixel

    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
    ش
    0.46
    ᱞ
    0.46
     diversi
    0.46
     Modular
    0.45
     conm
    0.45
     deploying
    0.44
     cajas
    0.44
     clones
    0.43
     modular
    0.42
    añ
    0.42
    POSITIVE LOGITS
     حيات
    0.50
    感到
    0.49
     மேலே
    0.48
    炽
    0.46
    丽
    0.45
    煌
    0.44
    stedet
    0.44
    讵
    0.44
     רא
    0.43
    喜爱
    0.43
    Activations Density 0.000%

    No Known Activations