© 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. 183769
    Prev
    Next
    INDEX
    Explanations

    lovely son, dumpster will, advertising community

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

    Monitoring, filtering, labels, literature regarding

    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
    vadipine
    0.58
    摡
    0.57
    ਵਾਈ
    0.49
    引起
    0.48
     सस्ती
    0.48
     EQUITY
    0.47
    ड़ों
    0.46
    umbing
    0.46
     الحديث
    0.46
     도움이
    0.46
    POSITIVE LOGITS
     Wilt
    0.46
     Zoe
    0.45
     Reveal
    0.45
     did
    0.44
    হ্য
    0.44
    h
    0.43
    f
    0.43
     h
    0.43
     fl
    0.43
     bash
    0.43
    Activations Density 0.000%

    No Known Activations