© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 210327
    Prev
    Next
    INDEX
    Explanations

    save or provide

    np_acts-logits-general · gemini-2.5-flash-lite

    defining a list

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    urro
    0.45
    ියේ
    0.43
     ждать
    0.43
    ur
    0.41
    ][_
    0.41
    çon
    0.41
     اللجنة
    0.41
    出国
    0.40
     国
    0.40
    盯
    0.40
    POSITIVE LOGITS
    Typically
    0.59
     toxicants
    0.55
    Well
    0.52
    TERY
    0.51
     Typically
    0.50
     Occ
    0.50
     Cari
    0.50
    Every
    0.47
    Dimensional
    0.47
     Everyday
    0.47
    Activations Density 0.000%

    No Known Activations