© 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. 26151
    Prev
    Next
    INDEX
    Explanations

    Hugging Face model repository paths

    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
     فران
    0.41
     پیپلز
    0.41
     शिवसेने
    0.40
     주요
    0.39
     CAGR
    0.39
     createState
    0.38
     효
    0.38
    Ფ
    0.38
     государственных
    0.38
     ప్రో
    0.38
    POSITIVE LOGITS
    _
    0.54
    -
    0.53
    izard
    0.43
    hk
    0.42
    rotated
    0.41
    ista
    0.40
    igu
    0.40
    sof
    0.40
    ih
    0.39
    vb
    0.39
    Activations Density 0.004%

    No Known Activations