© 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. 75373
    Prev
    Next
    INDEX
    Explanations

    vote, anglers, government, umbrella, breath

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

    avoid escalating situations

    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
    ાઇન
    0.49
     निशाना
    0.48
    فيذ
    0.46
    ंक्शन
    0.45
    λος
    0.44
    汽車
    0.44
    加油
    0.44
    ឍ
    0.44
    ट्टे
    0.44
    gifter
    0.44
    POSITIVE LOGITS
     I
    0.57
     Some
    0.55
     More
    0.52
     api
    0.52
     Má
    0.51
     Sche
    0.50
     Y
    0.50
     sometimes
    0.50
     Sometimes
    0.49
     Let
    0.48
    Activations Density 0.002%

    No Known Activations