© 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. 12428
    Prev
    Next
    INDEX
    Explanations

    or and archives

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

    asking me about my

    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
    連合
    0.43
    ր
    0.42
    成像
    0.41
    р
    0.41
    ห์
    0.40
    ์
    0.40
    次元
    0.39
    れ
    0.39
     covariant
    0.39
    渉
    0.39
    POSITIVE LOGITS
    ską
    0.52
     mujhe
    0.51
     مجھے
    0.49
     бясплат
    0.49
    íveis
    0.48
     weekdays
    0.48
     amplo
    0.46
    ခန်း
    0.46
     manually
    0.46
    مجھے
    0.44
    Activations Density 0.000%

    No Known Activations