© 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. 176847
    Prev
    Next
    INDEX
    Explanations

    Priyanka organization berry

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

    seeking or wanting outcomes

    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
    else
    0.52
    aites
    0.49
     cyt
    0.48
    ’
    0.46
    us
    0.46
    iii
    0.43
    (),
    0.43
    از
    0.43
    ا
    0.43
    ris
    0.42
    POSITIVE LOGITS
    𒆜
    0.49
    গম
    0.48
     Bücher
    0.47
     GTEST
    0.46
     Oni
    0.45
     messageShow
    0.45
     বুঝতে
    0.45
     tanti
    0.45
     ROUILLER
    0.45
     বড়ই
    0.44
    Activations Density 0.001%

    No Known Activations