© 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. 5514
    Prev
    Next
    INDEX
    Explanations

    hundreds of thousands of spectators

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

    Serial output and code

    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
    omot
    0.52
     vattum
    0.51
    ዢ
    0.48
    ክምና
    0.48
     courbes
    0.46
    меры
    0.46
    ایہ
    0.45
     கேட்டு
    0.45
     mempelajari
    0.45
    Lus
    0.45
    POSITIVE LOGITS
     for
    0.62
     (
    0.53
    UB
    0.51
     organisers
    0.51
     and
    0.51
     [
    0.51
     AND
    0.49
    la
    0.49
    HEL
    0.49
     #
    0.49
    Activations Density 0.000%

    No Known Activations