© 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. 87740
    Prev
    Next
    INDEX
    Explanations

    items being created or described

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

    rules and regulations

    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
     h
    0.43
    是要
    0.43
     boolean
    0.41
     هت
    0.41
     Anatomy
    0.41
     জাতিকে
    0.40
    β
    0.40
    要有
    0.39
    ವರಿಗೆ
    0.39
    وى
    0.39
    POSITIVE LOGITS
    бле
    0.57
     spectrosc
    0.55
    agregar
    0.50
    꿇
    0.49
     кеңсеси
    0.49
     descobrir
    0.48
     coleta
    0.48
     agregó
    0.48
    ilizar
    0.48
     détecter
    0.47
    Activations Density 0.000%

    No Known Activations