© 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. 146702
    Prev
    Next
    INDEX
    Explanations

    according to

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

    contrast and concession clauses

    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
    运动
    0.50
    🪐
    0.49
    适合
    0.48
    欧洲
    0.48
    ática
    0.48
     ம
    0.48
    们的
    0.48
    会让
    0.47
    ّة
    0.46
    无法
    0.46
    POSITIVE LOGITS
     following
    0.52
     although
    0.52
     according
    0.52
     assessments
    0.44
     but
    0.44
     instituted
    0.43
     preceded
    0.43
     though
    0.42
     marking
    0.41
     outcrops
    0.41
    Activations Density 0.000%

    No Known Activations