© 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. 164909
    Prev
    Next
    INDEX
    Explanations

    business, corporate, and financial terms

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

    process volume

    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
     座
    0.49
     dak
    0.47
    INO
    0.46
    fe
    0.46
    ETA
    0.46
     предложение
    0.46
    MN
    0.45
    MG
    0.45
    ENTA
    0.45
    BT
    0.45
    POSITIVE LOGITS
    colare
    0.46
    க்கொண்டு
    0.46
    ೪
    0.45
    льными
    0.44
    abbanti
    0.43
    اک
    0.42
    様な
    0.42
    ன்
    0.42
    ătur
    0.42
     ቅር
    0.42
    Activations Density 0.000%

    No Known Activations