© 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. 191169
    Prev
    Next
    INDEX
    Explanations

    version, pair of, drawer of, the essence, significant growth

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

    understanding social cues

    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
    他
    0.52
     jobNumber
    0.51
     אך
    0.49
    "
    0.48
     constricted
    0.48
     שט
    0.48
     nus
    0.47
    藁
    0.47
    器官
    0.47
     其他
    0.46
    POSITIVE LOGITS
    award
    0.52
    have
    0.49
     entreprises
    0.49
    lees
    0.48
    oble
    0.48
    au
    0.47
    ouss
    0.47
     entreprise
    0.46
    CCI
    0.46
    raise
    0.46
    Activations Density 0.000%

    No Known Activations