© 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. 218497
    Prev
    Next
    INDEX
    Explanations

    precursor electronics nightlife kindly gifted

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

    special promotions or status

    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
    ylmethylsulfanyl
    0.46
    Implicit
    0.43
    Applic
    0.42
     ગાંધી
    0.42
    ଣ
    0.41
     declar
    0.41
    OpenCamera
    0.41
     resist
    0.41
    西
    0.41
     ಗೌ
    0.40
    POSITIVE LOGITS
    鵬
    0.49
     perfected
    0.48
    ライン
    0.47
     Kleine
    0.46
     pien
    0.45
    鹏
    0.44
     mastered
    0.43
     aikana
    0.43
     finalized
    0.43
     tems
    0.43
    Activations Density 0.001%

    No Known Activations