© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 95493
    Prev
    Next
    INDEX
    Explanations

    financial transactions or costs

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

    quantitative skills and technology

    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
    ᱕
    0.48
    Anyways
    0.46
     চৈতন্যের
    0.45
    llvm
    0.45
     Anyways
    0.45
     えっと
    0.44
    自分が
    0.44
    ພວກເຮົາ
    0.44
     გას
    0.44
     sharpness
    0.43
    POSITIVE LOGITS
     bande
    0.49
     الغ
    0.46
    s
    0.46
     UW
    0.45
     ancora
    0.45
     of
    0.44
     Tiro
    0.44
    b
    0.44
     Band
    0.44
     الشريط
    0.43
    Activations Density 0.000%

    No Known Activations