© 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. 144566
    Prev
    Next
    INDEX
    Explanations

    an operating, to help, majority of, unto me

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

    following up, clarification, or subjects

    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
    तून
    0.49
     ineffective
    0.48
     exploiting
    0.46
     wund
    0.46
     intégral
    0.46
     ABCD
    0.45
     exploited
    0.45
    ://${
    0.44
     disturbed
    0.44
    ंना
    0.44
    POSITIVE LOGITS
    ahr
    0.50
     परसेंटेज
    0.50
    ಯೋಗ
    0.49
    prevState
    0.48
    profissional
    0.47
    uf
    0.46
    ju
    0.46
    ira
    0.46
     прибли
    0.46
    ica
    0.45
    Activations Density 0.000%

    No Known Activations