© 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. 174991
    Prev
    Next
    INDEX
    Explanations

    belong to

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

    trained on

    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
     ሁሉም
    0.54
     ຮ
    0.53
    ﺑ
    0.53
     ဆ
    0.52
    েন্দ্রলাল
    0.50
     লেফটেন্যান্ট
    0.50
     স্বামী
    0.50
     ਸੀ
    0.49
    ≲
    0.47
     ሂደ
    0.46
    POSITIVE LOGITS
    (
    0.49
    otu
    0.48
     devol
    0.48
     .
    0.47
    re
    0.46
    vu
    0.44
     pasar
    0.44
     USART
    0.43
     recog
    0.43
    abu
    0.43
    Activations Density 0.000%

    No Known Activations