© 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. 41-GEMMASCOPE-2-RES-262K
    7. 21558
    Prev
    Next
    INDEX
    Explanations

    volume quantification

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    nextToken
    0.43
    咉
    0.41
     نیر
    0.41
    าระ
    0.41
    াকর্ম
    0.40
    ኙ
    0.39
    主播
    0.38
    険
    0.37
     ঘা
    0.37
    ِمض
    0.37
    POSITIVE LOGITS
     volume
    2.81
     Volume
    2.55
    Volume
    2.53
    volume
    2.52
     volumes
    2.48
     volumen
    2.38
     VOLUME
    2.22
     Volumen
    2.20
     Volumes
    2.16
     volum
    2.14
    Activations Density 0.013%

    No Known Activations