© 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. 18692
    Prev
    Next
    INDEX
    Explanations

    line ofthe morning

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

    technical, foreign, or specific names

    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
    ুস
    0.48
    ু
    0.48
    ন্দ
    0.46
    also
    0.46
    也有
    0.45
    也
    0.45
    弥
    0.44
    ский
    0.44
    及
    0.44
    IR
    0.43
    POSITIVE LOGITS
     jedno
    0.55
     abon
    0.53
     صارفین
    0.49
     overfitting
    0.48
     okup
    0.48
    reon
    0.47
     σήμερα
    0.46
     搭
    0.46
     Auguste
    0.45
     Landon
    0.45
    Activations Density 0.000%

    No Known Activations