© 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. 112900
    Prev
    Next
    INDEX
    Explanations

    foreign language numbers

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

    batch script or file

    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
    בר
    0.49
    캄
    0.49
    טורק
    0.48
    fim
    0.48
    چین
    0.48
     lai
    0.46
    ಲಾ
    0.46
    รัส
    0.46
    мережа
    0.45
    우
    0.45
    POSITIVE LOGITS
     δύο
    0.50
     ইতিহাসের
    0.49
     Recht
    0.47
     ৭৮
    0.47
     எது
    0.47
     أن
    0.46
     desarrolló
    0.46
    রের
    0.46
    :
    0.46
     अवधारणा
    0.45
    Activations Density 0.001%

    No Known Activations