© 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. 176417
    Prev
    Next
    INDEX
    Explanations

    design engineering class

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

    new sequences and changes

    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
    PL
    0.50
    ↵
    0.44
    {
    0.43
    外的
    0.43
    GEM
    0.42
     K
    0.42
    versus
    0.41
    wehr
    0.41
    K
    0.41
    RAM
    0.40
    POSITIVE LOGITS
     thậm
    0.55
     liturgical
    0.54
     envío
    0.53
     новые
    0.52
     nuevos
    0.52
     جدید
    0.51
     cambió
    0.50
     nové
    0.50
     ახ
    0.49
     cambios
    0.49
    Activations Density 0.000%

    No Known Activations