© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 98889
    Prev
    Next
    INDEX
    Explanations

    easy access, quick access

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

    translate complex business

    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
     costumbre
    0.46
    のアレンジ
    0.43
     колон
    0.41
     IANS
    0.41
     ZTE
    0.41
    同
    0.41
    太多
    0.40
    必須
    0.40
     hona
    0.40
     reikia
    0.40
    POSITIVE LOGITS
    ecological
    0.43
     পরিকল্পিত
    0.42
     cuộc
    0.40
     Arc
    0.39
     Progress
    0.38
     Linden
    0.38
    经过
    0.38
    érée
    0.38
    zeczy
    0.38
    ger
    0.38
    Activations Density 0.001%

    No Known Activations