© 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. 52277
    Prev
    Next
    INDEX
    Explanations

    catching you, felt excited

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

    prioritize, ideal best for

    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
     facsimile
    0.52
     nominally
    0.45
     .
    0.45
     construe
    0.44
     his
    0.44
     sumptuous
    0.44
     sexual
    0.43
     /
    0.43
     er
    0.43
     constitute
    0.43
    POSITIVE LOGITS
     ప్రస్తుతం
    0.51
    ওয়ান
    0.50
    सरत
    0.49
     підпри
    0.47
    数字化
    0.46
    анта
    0.46
     युवाओं
    0.45
     থাকলেও
    0.44
     भेड़
    0.44
    껏
    0.44
    Activations Density 0.000%

    No Known Activations