© 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. 241632
    Prev
    Next
    INDEX
    Explanations

    fintech

    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
    䒷
    0.53
     рукой
    0.51
     digo
    0.48
     niego
    0.47
     dejó
    0.45
    㧕
    0.44
    cześ
    0.44
    latego
    0.44
    我看
    0.44
    thorace
    0.43
    POSITIVE LOGITS
     Xiaomi
    0.45
     Software
    0.41
    を実施
    0.41
     chatbots
    0.40
     fintech
    0.40
    賃
    0.40
     Fintech
    0.39
    招聘
    0.39
     instanceof
    0.38
     Webinar
    0.38
    Activations Density 0.002%

    No Known Activations