© 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-262K
    7. 215399
    Prev
    Next
    INDEX
    Explanations

    private/public declarations

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    renz
    0.40
    𝘦
    0.37
    𓏧
    0.37
    orean
    0.36
    queleto
    0.35
    reads
    0.35
     アクセサリー
    0.35
    
    0.35
    prac
    0.35
    Many
    0.34
    POSITIVE LOGITS
     episode
    0.42
     at
    0.39
     SUBTOTAL
    0.39
     takeaway
    0.38
     самостоятельно
    0.38
     будущего
    0.38
     butternut
    0.38
     miz
    0.37
    ர்ச்ச
    0.37
    ടി
    0.37
    Activations Density 0.001%

    No Known Activations