© 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. 126050
    Prev
    Next
    INDEX
    Explanations

    raised against

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

    revenue growth and sales

    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
    修订
    0.48
    ensions
    0.44
    浏
    0.44
    hep
    0.43
     సు
    0.43
    Microsoft
    0.42
    Embed
    0.42
    错过
    0.41
    了一种
    0.40
    였습니다
    0.40
    POSITIVE LOGITS
     sales
    0.53
    醬
    0.51
     Producto
    0.51
     produkcji
    0.51
    銷售
    0.50
     बिक्री
    0.50
     salesman
    0.49
     craftsman
    0.49
     SALES
    0.48
     shelves
    0.47
    Activations Density 0.000%

    No Known Activations