© 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. 114636
    Prev
    Next
    INDEX
    Explanations

    servers virtual infrastructure

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

    string item identifiers

    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
    ेड
    0.54
    ম
    0.51
    므
    0.50
    с
    0.48
    ม
    0.48
    al
    0.48
    予想
    0.47
    Ē
    0.47
    ãos
    0.47
    ாட
    0.46
    POSITIVE LOGITS
    ক্ষণের
    0.43
    قسم
    0.42
     NRC
    0.41
     hlavní
    0.40
    قيم
    0.40
    tween
    0.40
     hurling
    0.39
    NRC
    0.39
     quizz
    0.39
    verkehr
    0.39
    Activations Density 0.000%

    No Known Activations