© 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. 156945
    Prev
    Next
    INDEX
    Explanations

    decisions based, award of, Epidiolex

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

    conversations, threads, practical, artist, strengthen, work

    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
    OnOff
    0.47
    ClickHandler
    0.46
    벅
    0.46
     табы
    0.45
     సూ
    0.45
    Celltype
    0.44
     יע
    0.44
    stätte
    0.44
     соответствии
    0.44
     боле
    0.43
    POSITIVE LOGITS
    m
    0.58
     Guillermo
    0.57
     outfielder
    0.54
     The
    0.52
     El
    0.51
    s
    0.49
    lim
    0.49
     IW
    0.48
     Dmitri
    0.48
    adding
    0.47
    Activations Density 0.001%

    No Known Activations