© 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. 69475
    Prev
    Next
    INDEX
    Explanations

    supplement or advert related phrases

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

    concepts, technical terms, descriptions

    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
     clandestine
    0.54
     imassa
    0.50
     devre
    0.48
     домаћинствима
    0.47
    ilibus
    0.47
    otesi
    0.45
    aparikkh
    0.45
     返
    0.45
     DENUMIRE
    0.44
    คคล
    0.44
    POSITIVE LOGITS
     مي
    0.43
    દી
    0.41
    يج
    0.41
     ingles
    0.41
    Artists
    0.40
    Southeast
    0.40
     avenida
    0.40
    മെ
    0.40
    ølge
    0.40
    <html>
    0.39
    Activations Density 0.000%

    No Known Activations