© 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. 172955
    Prev
    Next
    INDEX
    Explanations

    available, partner, lads, website

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

    countries and AI

    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
    Arctic
    0.56
     Arctic
    0.48
    Sun
    0.43
     headspace
    0.43
    scar
    0.43
    Sunflower
    0.43
     .
    0.43
     zero
    0.42
    #
    0.42
    Tropical
    0.42
    POSITIVE LOGITS
    嘍
    0.55
    網站
    0.53
    𝗷
    0.51
    𝘷
    0.50
    怅
    0.50
    納期
    0.50
     služby
    0.49
    能力的
    0.48
    后者
    0.48
    वेदना
    0.48
    Activations Density 0.000%

    No Known Activations