© 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. 219035
    Prev
    Next
    INDEX
    Explanations

    Hungarian folk, her dog

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

    Laravel facades and related concepts

    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
     子供
    0.50
     বছর
    0.49
     ವರ್ಷ
    0.49
    㑅
    0.49
     tahun
    0.46
     多い
    0.46
    বছর
    0.45
     }{
    0.45
     Stratford
    0.45
     Brist
    0.44
    POSITIVE LOGITS
    ان
    0.52
    Q
    0.52
    ي
    0.50
    猜测
    0.50
    Departamento
    0.47
    R
    0.47
    ل
    0.46
    يان
    0.46
    ی
    0.46
    يون
    0.46
    Activations Density 0.000%

    No Known Activations