© 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. 130541
    Prev
    Next
    INDEX
    Explanations

    expeditions, Phật, or use

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

    technical and categorical terms

    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
    謦
    0.43
    ısından
    0.42
     cumbersome
    0.40
    Different
    0.39
    层
    0.39
    惩
    0.38
    Control
    0.38
    短信
    0.38
    ：
    0.38
    Random
    0.38
    POSITIVE LOGITS
     utilisent
    0.45
     quando
    0.45
     amikor
    0.45
     expeditions
    0.44
     Phật
    0.44
     použití
    0.44
     fyrir
    0.44
     vudd
    0.43
     toegang
    0.43
     cuando
    0.43
    Activations Density 0.000%

    No Known Activations