© 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. 192242
    Prev
    Next
    INDEX
    Explanations

    caustic, enjoyment, everywhere

    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
    alta
    0.42
     vectorial
    0.37
    롯
    0.36
     परेड
    0.35
     intermittent
    0.35
    >→</
    0.34
     заку
    0.33
    alto
    0.33
     renounce
    0.33
    sid
    0.32
    POSITIVE LOGITS
    鄯
    0.41
    rianças
    0.37
     FIB
    0.37
     motivation
    0.36
    WING
    0.36
    reetings
    0.36
     الزمن
    0.36
    ൽപ്പ
    0.35
    RAFT
    0.35
    ROC
    0.35
    Activations Density 0.002%

    No Known Activations