© 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. 189095
    Prev
    Next
    INDEX
    Explanations

    confidence, date, materials

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

    combinations, seasons, mothers, iter

    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
     precipitates
    0.55
    lardan
    0.55
    ları
    0.53
    ی
    0.52
    ים
    0.51
     doesn
    0.50
    lerden
    0.49
     subjet
    0.49
    ς
    0.48
    aeus
    0.48
    POSITIVE LOGITS
    Brian
    0.47
    最低
    0.46
    開始
    0.45
     Brian
    0.44
    ृह
    0.44
    urig
    0.43
    ioniert
    0.42
     ऊपरी
    0.42
    Hö
    0.42
    時間が
    0.41
    Activations Density 0.001%

    No Known Activations