© 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. 63700
    Prev
    Next
    INDEX
    Explanations

    advocate for, fully constitutionally

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

    lists, and romanised text

    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
    tai
    0.44
     Wärme
    0.43
     heiß
    0.40
     stage
    0.40
    δει
    0.40
     αυ
    0.39
     heat
    0.39
    おい
    0.39
     gro
    0.39
     ಏ
    0.39
    POSITIVE LOGITS
     immunoblot
    0.51
     condiv
    0.50
    カウンター
    0.49
     diminue
    0.49
    TakeVideo
    0.49
     préférences
    0.48
     Chiron
    0.48
    CFBundle
    0.48
    MacroExpansion
    0.48
    propoxy
    0.48
    Activations Density 0.000%

    No Known Activations