© 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. 125640
    Prev
    Next
    INDEX
    Explanations

    business, finance, or legal terms

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

    demonstrate tasks

    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
    cable
    0.46
     szczególnie
    0.44
    ካከል
    0.43
     personer
    0.41
    maintain
    0.41
    स्ट्री
    0.41
     covenant
    0.40
    𝒋
    0.40
     যারা
    0.39
    Allows
    0.39
    POSITIVE LOGITS
     fluct
    0.45
     দৈনিক
    0.43
     جشنواره
    0.43
     Xinhua
    0.42
     nuôi
    0.41
     Zent
    0.40
     seguirá
    0.40
    Xinhua
    0.39
     figlio
    0.39
     Grafik
    0.39
    Activations Density 0.000%

    No Known Activations