© 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. 136096
    Prev
    Next
    INDEX
    Explanations

    season, curriculum, lesson

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

    VR glasses

    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
     экземпля
    0.51
    చె
    0.50
    This
    0.49
    锞
    0.48
    電話
    0.47
    цька
    0.47
     альбо
    0.47
     電話
    0.46
    ციის
    0.46
    เคย
    0.45
    POSITIVE LOGITS
    n
    0.50
     univers
    0.46
    arın
    0.46
     mundo
    0.45
     X
    0.44
     earthen
    0.43
    anian
    0.43
     Univers
    0.42
    nX
    0.42
     mixed
    0.42
    Activations Density 0.002%

    No Known Activations