© 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. 159178
    Prev
    Next
    INDEX
    Explanations

    important role, save time, sling to treat

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

    medical, UI, and work context

    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
    কে
    0.52
    ထား
    0.50
     سين
    0.46
    擾
    0.45
    璀
    0.44
    歡
    0.43
    有點
    0.43
    徇
    0.43
    ßen
    0.42
    ಿವೆ
    0.42
    POSITIVE LOGITS
     jika
    0.47
     muere
    0.47
     membaca
    0.46
     dacă
    0.45
    rilor
    0.45
     vagas
    0.44
     eikä
    0.43
     mampu
    0.43
     baca
    0.42
    рифмети
    0.42
    Activations Density 0.001%

    No Known Activations