© 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. 72586
    Prev
    Next
    INDEX
    Explanations

    Returning to, working through, named together, back to

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

    consistently reliable

    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
     предела
    0.60
    പക്ഷം
    0.58
     ক্ষেত্র
    0.57
    𝔀
    0.53
    к
    0.50
    があれば
    0.49
     нуле
    0.49
     близь
    0.48
     всеки
    0.48
     дворе
    0.48
    POSITIVE LOGITS
    letta
    0.50
     Manners
    0.49
    attet
    0.48
    ἵ
    0.47
     Dani
    0.46
     (
    0.46
     Deutschland
    0.45
     Dan
    0.44
     stated
    0.44
    adhi
    0.44
    Activations Density 0.000%

    No Known Activations