© 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. 66539
    Prev
    Next
    INDEX
    Explanations

    digitization of archives and papers

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

    digitizing content and archives

    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
    removed
    0.56
    öst
    0.54
    neither
    0.52
    ship
    0.51
    a
    0.50
    st
    0.50
    delimiter
    0.49
    ö
    0.49
    after
    0.49
    ato
    0.49
    POSITIVE LOGITS
     trunks
    0.49
     gelegen
    0.48
     greenhouses
    0.47
     প্রতিহিংস
    0.47
     temples
    0.46
     ఇప్పటికే
    0.45
    ورية
    0.43
     große
    0.42
    рах
    0.42
     Barcl
    0.42
    Activations Density 0.001%

    No Known Activations