© 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. 144401
    Prev
    Next
    INDEX
    Explanations

    agreement and specific groups

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

    URLs and ancestors

    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
    ג
    0.51
     Schuh
    0.50
    记载
    0.50
    fileName
    0.49
    Z
    0.48
     ISNI
    0.46
    㸵
    0.46
    ۇر
    0.46
     Rodriguez
    0.45
    ROI
    0.45
    POSITIVE LOGITS
     semifinals
    0.46
     polynomials
    0.45
     moins
    0.45
     esfuerzos
    0.45
     plasmids
    0.44
     cramps
    0.44
     krát
    0.44
     sensors
    0.43
     ग्राहकों
    0.43
    ان
    0.42
    Activations Density 0.001%

    No Known Activations