© 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. 134656
    Prev
    Next
    INDEX
    Explanations

    compounding store and bureaucratic reform

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

    calories, hold, seek, feed, novel

    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
    )){
    0.47
     Concepción
    0.45
    eské
    0.44
    šli
    0.44
     tudi
    0.44
    Shares
    0.44
     المحلي
    0.43
    apellido
    0.43
     чрезвы
    0.43
    ř
    0.43
    POSITIVE LOGITS
     derailed
    0.51
     hypotheses
    0.49
     Frege
    0.48
    ায়ক
    0.47
     precepts
    0.47
     Poem
    0.47
    প্রধানমন্ত্রী
    0.46
     refreshments
    0.46
    ಪ್ರ
    0.46
    ครั้ง
    0.46
    Activations Density 0.001%

    No Known Activations