© 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. 129140
    Prev
    Next
    INDEX
    Explanations

    shipping, article, to work

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

    awards, historical mentions, missing data, prices

    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
    ந
    0.52
    अंग्रे
    0.50
    是什么
    0.50
    빼
    0.49
    เว็บ
    0.48
    諜
    0.48
    ナイト
    0.47
    լ
    0.47
    是没有
    0.46
     बुखार
    0.46
    POSITIVE LOGITS
     hedon
    0.57
     Hendrick
    0.55
     HAVE
    0.52
     transaction
    0.49
     poly
    0.47
     determine
    0.46
     receptor
    0.45
     Hendrik
    0.45
     benchmark
    0.45
     resettlement
    0.45
    Activations Density 0.008%

    No Known Activations