© 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. 240791
    Prev
    Next
    INDEX
    Explanations

    multi-lingual concepts

    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
    besch
    0.50
    לחמת
    0.50
    f
    0.49
    ాను
    0.48
    archiv
    0.46
     esche
    0.46
    tel
    0.45
     ench
    0.44
    c
    0.44
    坚
    0.44
    POSITIVE LOGITS
    രാണ്
    0.49
     परिवर्तन
    0.47
     teoria
    0.47
     teor
    0.46
     mẽ
    0.44
     classica
    0.44
    來
    0.43
     ಲಿ
    0.43
     liu
    0.42
     rho
    0.42
    Activations Density 0.000%

    No Known Activations