© 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. 117728
    Prev
    Next
    INDEX
    Explanations

    common sentence connectors

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

    solutions, delivery, breeds, submission

    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
     Hui
    0.52
     Refresh
    0.45
     Relax
    0.44
    is
    0.43
     Able
    0.43
     j
    0.42
    Résumé
    0.42
     to
    0.42
     Glory
    0.42
     Mighty
    0.41
    POSITIVE LOGITS
     fabrics
    0.48
    łącznie
    0.48
     ٹیکسٹ
    0.48
    药品
    0.45
    걍
    0.44
    FLD
    0.44
    ッキング
    0.44
     betrokken
    0.44
    炖
    0.43
     дис
    0.43
    Activations Density 0.001%

    No Known Activations