© 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. 242591
    Prev
    Next
    INDEX
    Explanations

    non-english words

    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
    敏
    0.49
     younger
    0.44
     McIl
    0.44
    cach
    0.43
    很多的
    0.43
     ferv
    0.42
     Maxine
    0.42
     cleaner
    0.42
     Raum
    0.41
    年轻
    0.40
    POSITIVE LOGITS
    輥
    0.48
     ఒప్ప
    0.46
     खिलाफ
    0.46
     विरुद्ध
    0.46
    Від
    0.46
     उदासीन
    0.45
    ಿದ್ದ
    0.43
    יש
    0.43
    秝
    0.43
    ığı
    0.43
    Activations Density 0.000%

    No Known Activations