© 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. 39789
    Prev
    Next
    INDEX
    Explanations

    shipping to destinations

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

    historical context U value updated

    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
     முத
    0.48
     Proc
    0.44
     Discovery
    0.42
    ferd
    0.42
     NEVER
    0.41
    綿
    0.41
    exper
    0.41
    el
    0.41
    切
    0.40
    の商品
    0.40
    POSITIVE LOGITS
     stanno
    0.54
     finesse
    0.53
     อย่าง
    0.52
     pessoais
    0.49
     vidéo
    0.48
     кое
    0.48
     aspetto
    0.48
    क्राफ्ट
    0.48
     днів
    0.47
     chicos
    0.47
    Activations Density 0.000%

    No Known Activations