© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13856
    Prev
    Next
    INDEX
    Explanations

    programming variables and strings

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

    code output and definitions

    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_16k_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
    atgu
    0.46
    RequestParam
    0.43
     વધારે
    0.43
    婦
    0.43
    setdefault
    0.43
    galactos
    0.43
     vrouwen
    0.42
    信用卡
    0.42
     lact
    0.42
    svm
    0.42
    POSITIVE LOGITS
    변
    0.44
     Variablen
    0.41
     ಶಾ
    0.41
    Clark
    0.39
    yler
    0.39
    Dated
    0.38
     переменных
    0.38
     Varsity
    0.38
    TJ
    0.38
    시기
    0.38
    Activations Density 0.009%

    No Known Activations