© 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. 244341
    Prev
    Next
    INDEX
    Explanations

    file a complaint

    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
    {
    0.59
    []{
    0.55
    party
    0.47
    Air
    0.47
    鼠标
    0.47
    에서
    0.46
    스
    0.46
    网
    0.46
    detect
    0.46
     एयर
    0.46
    POSITIVE LOGITS
     Schengen
    0.57
     interplay
    0.50
     Dangerous
    0.49
     dangere
    0.49
     Buckeyes
    0.48
     Atl
    0.47
     Schofield
    0.47
     Average
    0.47
     capric
    0.47
     dangereux
    0.46
    Activations Density 0.000%

    No Known Activations