© 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. 31251
    Prev
    Next
    INDEX
    Explanations

    financial or general concepts

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

    why it's happening

    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
     مە
    0.49
    toBe
    0.44
    s
    0.44
    阝
    0.43
    toHaveBeenCalled
    0.42
     Pann
    0.42
    ")
    0.42
     καθη
    0.41
    WebService
    0.41
    ɣ
    0.41
    POSITIVE LOGITS
    ब्र
    0.48
     leaks
    0.47
     financières
    0.47
    чною
    0.46
    сток
    0.45
    আচ্ছা
    0.44
    સ્ક
    0.44
     المالية
    0.44
     romanzo
    0.43
    ковий
    0.43
    Activations Density 0.001%

    No Known Activations