© 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. 40-GEMMASCOPE-2-RES-65K
    7. 47357
    Prev
    Next
    INDEX
    Explanations

    actions or specific things

    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_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    厂
    0.40
     buses
    0.40
    Innov
    0.38
    Bre
    0.38
     завод
    0.37
    стами
    0.37
    Puzzle
    0.36
    Province
    0.36
    Areas
    0.36
     orphanage
    0.36
    POSITIVE LOGITS
     etcétera
    0.50
    等等
    0.46
    }+...
    0.44
     वगैरह
    0.43
     etc
    0.43
     दिसते
    0.42
     ಒಳಗ
    0.41
    行動
    0.40
    லோச
    0.40
     ਨਹੀਂ
    0.40
    Activations Density 0.003%

    No Known Activations