© 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. 111573
    Prev
    Next
    INDEX
    Explanations

    Costco, member

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

    Cyrillic or Eastern European characters

    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
     actuellement
    0.55
    ても
    0.54
     également
    0.53
     situé
    0.52
     cré
    0.52
     détect
    0.52
     ተጨማሪ
    0.52
     서
    0.51
     করলেও
    0.51
     qualités
    0.51
    POSITIVE LOGITS
    D
    0.56
    д
    0.53
    в
    0.50
    LIBRARY
    0.48
    FI
    0.47
    р
    0.47
    د
    0.47
    T
    0.47
    ER
    0.46
    й
    0.46
    Activations Density 0.000%

    No Known Activations