© 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. 95383
    Prev
    Next
    INDEX
    Explanations

    year range separator

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

    providing information ethically

    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
    в
    0.54
    Thoughts
    0.52
    どう
    0.51
    돈
    0.50
    皐
    0.49
    皋
    0.48
    ଚ
    0.48
    スー
    0.47
    Введите
    0.45
    ニチイ
    0.45
    POSITIVE LOGITS
    rals
    0.48
    phalt
    0.47
     sells
    0.46
     संघ
    0.45
     quilt
    0.44
    langs
    0.44
     थेट
    0.44
    sembling
    0.44
    posed
    0.43
     jumps
    0.43
    Activations Density 0.002%

    No Known Activations