© 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. 47376
    Prev
    Next
    INDEX
    Explanations

    achieving goals and relationships

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

    code, math, and technical language

    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
    テ
    0.52
    expressing
    0.49
    蓮
    0.46
     collège
    0.46
    ξύ
    0.46
     protéger
    0.45
    ウン
    0.44
    コート
    0.44
    αυ
    0.44
    璉
    0.44
    POSITIVE LOGITS
    ur
    0.55
     PackageManager
    0.45
    这类
    0.45
     Apprentice
    0.44
     عملی
    0.44
     
    0.44
    কারীরা
    0.44
     Break
    0.44
    ()
    0.43
     awards
    0.43
    Activations Density 0.000%

    No Known Activations