© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 75614
    Prev
    Next
    INDEX
    Explanations

    drug claims, database, Robot, interview

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

    hackathon and hackweek events

    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
    Negative Logits
    स
    0.51
     ಕೋ
    0.50
    ducted
    0.50
    layered
    0.49
    science
    0.48
     කළ
    0.48
    ‌و
    0.48
    𝗱
    0.48
    ਫ਼
    0.47
     आस्ट्रेलिया
    0.47
    POSITIVE LOGITS
     Utils
    0.46
     Agricult
    0.45
    竞技
    0.44
     Vape
    0.44
     Vail
    0.43
     étend
    0.42
     VAC
    0.42
     randomIndex
    0.41
     herr
    0.41
     legitimately
    0.40
    Activations Density 0.001%

    No Known Activations