© 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. 31-GEMMASCOPE-2-RES-65K
    7. 56716
    Prev
    Next
    INDEX
    Explanations

    study ETH

    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_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     plufieurs
    0.55
     opérés
    0.53
    ষেধ
    0.52
    <unused557>
    0.51
    ક્ટ
    0.50
    ка
    0.50
    wyczaj
    0.49
     ব্যাপক
    0.48
    ジュアル
    0.48
     agricoles
    0.48
    POSITIVE LOGITS
     was
    0.49
     Rejo
    0.43
     Convention
    0.42
     construct
    0.41
     condemnation
    0.41
    Ο
    0.41
     is
    0.40
     regimes
    0.38
     نیاز
    0.38
    oelectric
    0.38
    Activations Density 0.001%

    No Known Activations