© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 48359
    Prev
    Next
    INDEX
    Explanations

    sociales, derivatives, technology

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    气
    0.48
    atthanam
    0.46
    Session
    0.46
    实际
    0.45
    License
    0.44
    FindingsRequest
    0.44
    Certification
    0.43
    绿色
    0.42
    间
    0.42
    getStatus
    0.42
    POSITIVE LOGITS
     וכ
    0.46
    ifiably
    0.45
    スル
    0.45
    ع
    0.45
     fuer
    0.44
     tomada
    0.44
     influencer
    0.43
    同學
    0.43
     Lehr
    0.43
    ループ
    0.42
    Activations Density 0.005%

    No Known Activations