© 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. 30180
    Prev
    Next
    INDEX
    Explanations

    conditions apply

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

    coding, app, work, construction

    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
    ດ້
    0.49
    μή
    0.43
    มาะ
    0.43
    aspid
    0.42
     Utara
    0.42
     створе
    0.41
    ôté
    0.41
    மக்கு
    0.41
    тим
    0.41
    с
    0.41
    POSITIVE LOGITS
     apiece
    0.43
     excision
    0.40
    }/\
    0.40
     مقدار
    0.39
     infotainment
    0.39
     معنات
    0.39
    famous
    0.39
     و
    0.38
    밥
    0.38
     bija
    0.38
    Activations Density 0.000%

    No Known Activations