© 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. 41221
    Prev
    Next
    INDEX
    Explanations

    also help

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

    technical or medical information

    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
    स्थित
    0.47
     его
    0.45
    军
    0.45
     губерна
    0.43
     често
    0.43
    гыз
    0.42
    耸
    0.42
     אַ
    0.42
    竞技
    0.42
     군
    0.42
    POSITIVE LOGITS
     radiographs
    0.47
     hyperglycemia
    0.45
     consumables
    0.45
     aliqu
    0.44
     digestible
    0.44
     lact
    0.44
     jelly
    0.43
     dehydrated
    0.42
     tablets
    0.41
     digestibility
    0.41
    Activations Density 0.000%

    No Known Activations