© 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. 212070
    Prev
    Next
    INDEX
    Explanations

    non-English words

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

    rumors, continual purification, project review

    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
                     
    0.46
    کي
    0.44
    0.43
    কেশ
    0.43
     ())
    0.42
     in
    0.42
    Trusted
    0.42
    kong
    0.42
    （
    0.41
              
    0.41
    POSITIVE LOGITS
     Министер
    0.54
     води
    0.53
    赸
    0.52
     न्याया
    0.50
     сты
    0.50
     ናቸው
    0.49
     እየ
    0.49
     че
    0.49
    인다
    0.48
     оке
    0.48
    Activations Density 0.000%

    No Known Activations