© 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. 47502
    Prev
    Next
    INDEX
    Explanations

    multi-script language classification

    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
    iare
    0.49
    plat
    0.47
    ih
    0.44
    ።
    0.44
    >();
    0.44
    uis
    0.43
     jab
    0.43
     occupé
    0.43
    >?,
    0.43
     何
    0.43
    POSITIVE LOGITS
     Understand
    0.45
    ड
    0.45
     Peny
    0.45
    सि
    0.44
    ون
    0.43
    我对
    0.43
    ্যন্তরীণ
    0.43
    স্য
    0.42
    तिक
    0.42
     Pusat
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.