© 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. 18694
    Prev
    Next
    INDEX
    Explanations

    variety of options

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

    macro vs common name

    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
    сных
    0.40
    addContainerGap
    0.40
     Signific
    0.40
    해가
    0.40
     Crossing
    0.38
     देतात
    0.38
    istosoma
    0.38
     Ñ
    0.38
    Š
    0.38
     Nesse
    0.37
    POSITIVE LOGITS
     orbiting
    0.42
     naughty
    0.41
     wavelength
    0.41
     violently
    0.41
     disqualified
    0.40
    λλην
    0.40
    ้ม
    0.40
     defiant
    0.40
     unruly
    0.40
    籍
    0.40
    Activations Density 0.006%

    No Known Activations