© 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-262K
    7. 135128
    Prev
    Next
    INDEX
    Explanations

    going today/well/questions

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Theoretically
    0.43
     NEVER
    0.42
    经验
    0.41
     deney
    0.41
     immoral
    0.41
    CreateCharacter
    0.41
    다면
    0.41
    yrıca
    0.40
    ີ
    0.40
    alarına
    0.40
    POSITIVE LOGITS
     നടത്തി
    0.45
     holds
    0.44
     betroffen
    0.44
     jagged
    0.41
     assesses
    0.41
    します
    0.40
    konen
    0.40
     konfigur
    0.40
     zeigt
    0.39
    adeon
    0.39
    Activations Density 0.008%

    No Known Activations