© 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. 169985
    Prev
    Next
    INDEX
    Explanations

    end-to-end Text

    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
     设备
    0.47
    파일
    0.46
     Dateien
    0.46
     бясплат
    0.46
     Số
    0.45
     실제로
    0.45
     गिन
    0.45
     αριθ
    0.44
    萧
    0.44
    FindFileData
    0.44
    POSITIVE LOGITS
     drunken
    0.42
    batches
    0.40
    eclampsia
    0.39
     greenish
    0.38
    fling
    0.38
     shredded
    0.38
    EtOH
    0.37
     booze
    0.37
     smugglers
    0.37
     EtOH
    0.37
    Activations Density 0.004%

    No Known Activations