© 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. 3127
    Prev
    Next
    INDEX
    Explanations

    code and data structures

    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
    従って
    0.39
    звание
    0.39
    
    0.38
    Interfaz
    0.36
     ग्रे
    0.35
    ښت
    0.35
     धीरे
    0.35
    ្ឋ
    0.35
    <unused338>
    0.35
     नाइन
    0.34
    POSITIVE LOGITS
    ()))
    0.38
    展開
    0.35
     क्या
    0.35
    기는
    0.35
     Transcript
    0.35
     connot
    0.35
     Statutory
    0.34
    外套
    0.34
     "(
    0.33
     $(
    0.33
    Activations Density 0.005%

    No Known Activations