© 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. 104700
    Prev
    Next
    INDEX
    Explanations

    deal, transaction, costs

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

    quantitative descriptions and stress

    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
    公司
    0.55
     showings
    0.50
    ని
    0.44
    線
    0.43
    ショー
    0.43
     decks
    0.42
    सेल
    0.42
     compañías
    0.42
    藍
    0.41
     companies
    0.41
    POSITIVE LOGITS
     एखा
    0.51
    inare
    0.47
     해당
    0.46
    orh
    0.43
    enfant
    0.42
     lest
    0.40
    дию
    0.40
     خفی
    0.40
     Verfü
    0.39
    inqui
    0.39
    Activations Density 0.001%

    No Known Activations