© 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. 179331
    Prev
    Next
    INDEX
    Explanations

    communication channels and vehicles

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

    non-English words

    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
    lor
    0.55
    larından
    0.53
    ’).
    0.52
    corp
    0.50
    覚え
    0.49
    ’),
    0.49
    €™
    0.48
     uttering
    0.48
     articles
    0.48
     underval
    0.47
    POSITIVE LOGITS
    馏
    0.52
     கவன
    0.51
    里程
    0.47
    пи
    0.46
     হ্যাঁ
    0.46
    ύν
    0.46
     QtGui
    0.45
    Measured
    0.44
     zkušen
    0.43
     كل
    0.42
    Activations Density 0.000%

    No Known Activations