© 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. 12750
    Prev
    Next
    INDEX
    Explanations

    travel and driving times

    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
    é
    0.64
    ä
    0.61
    č
    0.59
    á
    0.58
    ia
    0.57
    ak
    0.54
     "
    0.53
     '
    0.53
    š
    0.53
    was
    0.51
    POSITIVE LOGITS
    టీఎం
    0.51
    ВП
    0.49
     দেখিয়
    0.49
    فير
    0.49
     डोंगर
    0.46
     Uninstall
    0.46
    保障
    0.45
    厨房
    0.45
     ब्रेस्ट
    0.45
    গঠ
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.