© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 12274
    Prev
    Next
    INDEX
    Explanations

    contrast conjunctions and punctuation

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

    but, however, else, exceptions

    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_16k_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
    ロナ
    0.43
    ερ
    0.42
     ਤੇ
    0.40
     النج
    0.38
     തുടങ്ങി
    0.38
     உலோக
    0.38
    ର୍
    0.37
    ਿ
    0.37
    NEY
    0.36
     gero
    0.36
    POSITIVE LOGITS
     nhưng
    0.76
    겠지만
    0.76
    但是在
    0.75
     but
    0.71
     ولكن
    0.68
     lakini
    0.67
     लेकिन
    0.66
     Nhưng
    0.65
     પરંતુ
    0.62
    but
    0.61
    Activations Density 0.004%

    No Known Activations