© 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. 229389
    Prev
    Next
    INDEX
    Explanations

    would, will, effectively, plug

    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
    밋
    0.46
     Vậy
    0.45
     تاسو
    0.44
    믈
    0.44
     가장
    0.44
     Turbulence
    0.44
    эр
    0.43
    ımızın
    0.43
     Lichtenfels
    0.43
     erity
    0.43
    POSITIVE LOGITS
    鬥
    0.47
    VC
    0.46
     refused
    0.45
    ยอม
    0.45
    不想
    0.44
     "&#
    0.44
    想到
    0.44
     revoked
    0.43
     conced
    0.43
    真
    0.43
    Activations Density 0.000%

    No Known Activations