© 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. 137261
    Prev
    Next
    INDEX
    Explanations

    tap local

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

    look until

    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
    雵
    0.51
    하겠습니다
    0.50
    ას
    0.47
    人格
    0.46
    霭
    0.46
    ಲು
    0.46
    脾
    0.46
     부담
    0.46
    國內
    0.46
    気
    0.45
    POSITIVE LOGITS
     doctoral
    0.50
     k
    0.48
     di
    0.48
     titul
    0.48
     playwright
    0.47
     docker
    0.47
     Turing
    0.47
     titled
    0.47
     Noether
    0.46
     comest
    0.46
    Activations Density 0.000%

    No Known Activations