© 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. 147885
    Prev
    Next
    INDEX
    Explanations

    corporate and financial contexts

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

    questions and plans

    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
    遊戲
    0.45
    筷
    0.45
     testes
    0.45
    向上
    0.44
    游戏
    0.44
    pressed
    0.43
     botão
    0.43
     chival
    0.42
    坦克
    0.42
    も
    0.42
    POSITIVE LOGITS
    Types
    0.52
     corporate
    0.48
     Corporate
    0.47
     cashback
    0.46
    Corporate
    0.46
     корпора
    0.44
     reembolso
    0.44
    💁
    0.43
     corporates
    0.42
    मियल
    0.42
    Activations Density 0.002%

    No Known Activations