© 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-65K
    7. 44786
    Prev
    Next
    INDEX
    Explanations

    policy positions

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     forgiving
    0.47
     المستخدم
    0.43
     propriétaire
    0.40
     diámetro
    0.39
    ہرست
    0.39
     conteúdo
    0.39
    ঃ
    0.39
     toolbar
    0.38
     administração
    0.38
    మో
    0.38
    POSITIVE LOGITS
     allegation
    0.40
     解
    0.40
    äns
    0.39
    以色列
    0.38
    rological
    0.37
     Bernoulli
    0.37
     instinct
    0.36
    }$
    0.36
    𝗇
    0.36
     theoret
    0.36
    Activations Density 0.006%

    No Known Activations