© 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. 18553
    Prev
    Next
    INDEX
    Explanations

    call, subscribe, receiving, better

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

    insurance, games, AI, code, chess

    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
     Å
    0.52
     neder
    0.44
    ्युनिटी
    0.42
    राती
    0.41
    总经理
    0.40
     virtu
    0.39
    امر
    0.38
     å
    0.38
    uml
    0.38
    |+|
    0.38
    POSITIVE LOGITS
    กับ
    0.49
     ENGINEER
    0.48
     বিশেষ
    0.45
    の新
    0.45
     repositories
    0.44
    ヤマハ
    0.44
    綣
    0.44
    ρων
    0.43
     WHICH
    0.43
     コットン
    0.43
    Activations Density 0.000%

    No Known Activations