© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 201537
    Prev
    Next
    INDEX
    Explanations

    sales and financial patterns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ಥ
    0.54
     країни
    0.51
     ব্রাজ
    0.48
    ۶
    0.48
    ل
    0.46
    ڈر
    0.46
    رک
    0.46
    茍
    0.46
    ﾛ
    0.45
    ೧
    0.45
    POSITIVE LOGITS
    ed
    0.51
     Model
    0.47
     Hip
    0.46
     S
    0.46
    iao
    0.44
     Milestone
    0.44
     Student
    0.44
     ...,
    0.44
     Bing
    0.43
    amu
    0.42
    Activations Density 0.001%

    No Known Activations