© 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. 176431
    Prev
    Next
    INDEX
    Explanations

    running pants, shaped table, looking for

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

    arch support, fungi, timing

    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
    就会
    0.47
     હતો
    0.47
    GROUP
    0.45
    סה
    0.45
    નો
    0.44
    泄
    0.44
    شی
    0.44
    沨
    0.44
    网站
    0.43
    危机
    0.43
    POSITIVE LOGITS
     desolate
    0.46
    vey
    0.43
    vend
    0.43
    food
    0.42
     väldigt
    0.42
     indust
    0.42
     frequent
    0.42
     एनिम
    0.42
    하시는
    0.42
     curving
    0.42
    Activations Density 0.001%

    No Known Activations