© 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. 138727
    Prev
    Next
    INDEX
    Explanations

    directories, listings, and purchases

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

    Google TV, YouTube Shorts, months

    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
     fondamental
    0.48
    中断
    0.46
    缶
    0.46
    сько
    0.45
    擞
    0.45
    entan
    0.44
    тана
    0.44
     capítulo
    0.44
     círculo
    0.43
    中
    0.43
    POSITIVE LOGITS
     directories
    0.54
     purchases
    0.45
     brothers
    0.45
    directory
    0.45
    albums
    0.45
    andingan
    0.44
     vineyards
    0.44
     listings
    0.43
     REGIUNI
    0.43
    ⁶
    0.43
    Activations Density 0.001%

    No Known Activations