© 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. 183126
    Prev
    Next
    INDEX
    Explanations

    listing descriptions and features

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

    complex systems and states

    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
    rescue
    0.45
    ᙱ
    0.45
    summar
    0.45
    стым
    0.45
    セミ
    0.44
     Katie
    0.44
    propTypes
    0.44
    shifts
    0.43
    shields
    0.43
    シフト
    0.43
    POSITIVE LOGITS
    ^{
    0.54
     disgraced
    0.52
     hệ
    0.47
    proken
    0.45
    körper
    0.45
     einen
    0.45
    кар
    0.45
     cooled
    0.44
    厝
    0.44
     miệng
    0.44
    Activations Density 0.000%

    No Known Activations