© 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. 10800
    Prev
    Next
    INDEX
    Explanations

    solving and solutions

    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
    是一種
    0.43
     콘텐츠
    0.42
     rivulet
    0.41
     Research
    0.39
     audit
    0.38
    是一种
    0.38
    研发
    0.38
     Υ
    0.38
     έναν
    0.38
     Coating
    0.38
    POSITIVE LOGITS
    Sol
    0.52
    솔
    0.47
     Sol
    0.46
    SOL
    0.46
    sol
    0.46
    Sole
    0.46
    ClearedBy
    0.45
    ూ
    0.44
     soln
    0.44
    ติก
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.