© 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. 211644
    Prev
    Next
    INDEX
    Explanations

    legal, medical, factual contexts

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

    media activism

    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
    entiti
    0.52
    𝘴
    0.51
    羙
    0.51
    asiswa
    0.50
     پیشہ
    0.50
    zę
    0.49
    fehlung
    0.49
    вых
    0.48
    jegyz
    0.48
     Prevalence
    0.47
    POSITIVE LOGITS
     so
    0.53
     scoop
    0.52
     can
    0.52
     storm
    0.50
     penit
    0.49
     cathodes
    0.48
     (
    0.46
     gradual
    0.46
     psal
    0.46
     drives
    0.46
    Activations Density 0.002%

    No Known Activations