© 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. 190636
    Prev
    Next
    INDEX
    Explanations

    business executives

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

    business/finance terms

    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
    p
    0.57
    \}.
    0.52
    Cs
    0.49
    uos
    0.46
     seuls
    0.46
    ch
    0.45
    ppt
    0.45
    C
    0.45
    L
    0.45
    誼
    0.44
    POSITIVE LOGITS
    तरे
    0.50
     많
    0.47
    omiast
    0.47
     cannibal
    0.46
     निवेश
    0.46
     бизнес
    0.46
     vliegt
    0.45
     skyrocketing
    0.44
     fraudsters
    0.44
     executives
    0.44
    Activations Density 0.000%

    No Known Activations