© 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. 186662
    Prev
    Next
    INDEX
    Explanations

    work product or collection pieces

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

    canalysis, callback, discovery, adaptation

    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
     TLR
    0.53
     Sasha
    0.52
     仕
    0.48
     retail
    0.47
     endowment
    0.47
     retirement
    0.45
     veremos
    0.45
    orestation
    0.45
     sprzedaży
    0.45
     petting
    0.44
    POSITIVE LOGITS
    Newton
    0.51
    馀
    0.51
    ុង
    0.46
    ฟ
    0.46
    كان
    0.46
    姆斯
    0.46
    ై
    0.46
    凿
    0.46
    她们
    0.46
     corresponde
    0.45
    Activations Density 0.000%

    No Known Activations