© 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. 198715
    Prev
    Next
    INDEX
    Explanations

    specify lists, narrow enough

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

    determined by, requires knowing

    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
    Mot
    0.48
    Technologies
    0.47
    ലം
    0.46
     fermeture
    0.45
    Tere
    0.45
    P
    0.45
    UD
    0.44
    یکن
    0.44
    قا
    0.43
    سب
    0.43
    POSITIVE LOGITS
     डिटेल्स
    0.48
     नाटक
    0.48
     countryside
    0.46
    ுள்ளனர்
    0.45
     मजेदार
    0.44
     संबद्ध
    0.44
     Bingham
    0.44
    ギュア
    0.44
     Rhet
    0.44
     |_{
    0.43
    Activations Density 0.001%

    No Known Activations