© 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. 232131
    Prev
    Next
    INDEX
    Explanations

    fair market value or employment context

    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
    激烈
    0.47
    സോ
    0.47
    激
    0.47
     fø
    0.46
     doulou
    0.45
     enem
    0.44
    ന്നു
    0.44
     dessas
    0.44
     attaqu
    0.43
     فيها
    0.43
    POSITIVE LOGITS
    GH
    0.49
    Gh
    0.47
    otea
    0.46
     staircase
    0.46
    ג
    0.46
    BufferedReader
    0.44
    asgi
    0.44
    ہد
    0.44
    igh
    0.43
     Arom
    0.43
    Activations Density 0.002%

    No Known Activations