© 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. 30987
    Prev
    Next
    INDEX
    Explanations

    official capacity, wild symbols

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

    Pigeonhole, Innovators, Wine Bottle, X shape

    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
    依旧
    0.49
    Mos
    0.47
    越来越
    0.47
    ด
    0.46
    Partner
    0.46
    Miche
    0.45
    ก
    0.45
    慢慢
    0.45
    Lol
    0.44
    avon
    0.44
    POSITIVE LOGITS
     terdapat
    0.52
     Laboratories
    0.51
     Performances
    0.47
     garments
    0.45
     Religions
    0.45
     Punkte
    0.45
     Prisons
    0.45
     delegations
    0.45
     nations
    0.42
     Zahlen
    0.42
    Activations Density 0.000%

    No Known Activations