© 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. 109452
    Prev
    Next
    INDEX
    Explanations

    multilingual words and phrases

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

    flags, Global, individual, sun

    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
    غ
    0.49
    ưa
    0.47
    螻
    0.47
     mLast
    0.46
     caracteres
    0.46
     mView
    0.45
    闲
    0.44
    離
    0.44
    푐
    0.44
    淋
    0.43
    POSITIVE LOGITS
    купно
    0.51
     महा
    0.51
     세제곱
    0.49
     bahagia
    0.47
     মুজিবুর
    0.46
     vineyards
    0.45
     זיי
    0.45
     گلوکار
    0.45
     menciptakan
    0.45
    jung
    0.45
    Activations Density 0.000%

    No Known Activations