© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 22711
    Prev
    Next
    INDEX
    Explanations

    contrast or alternative

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

    contrasting or qualifying statements

    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
    Not in Any Lists

    No Comments

    Negative Logits
     沒有
    0.70
    봤
    0.69
    ဟုတ်
    0.66
     這個
    0.64
    နိုင်သည်။
    0.60
     ಯಾವುದೇ
    0.60
    也沒有
    0.59
     niektórych
    0.58
     我們
    0.58
     எதுவும்
    0.58
    POSITIVE LOGITS
     anzi
    0.65
     a
    0.65
     in
    0.63
    namely
    0.57
     juist
    0.56
    N
    0.55
     indeed
    0.53
    r
    0.53
    F
    0.52
    U
    0.50
    Activations Density 0.049%

    No Known Activations