© 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. 231967
    Prev
    Next
    INDEX
    Explanations

    business, sales, law, finance

    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
    ك
    0.46
    付
    0.46
    良
    0.45
    L
    0.44
    解
    0.44
    三
    0.43
    ktan
    0.43
    خود
    0.43
     iklan
    0.43
    1
    0.43
    POSITIVE LOGITS
     эту
    0.55
     развития
    0.54
    attho
    0.53
     развитие
    0.52
     функциони
    0.52
     границ
    0.52
     발생
    0.50
     ద్వారా
    0.50
     використання
    0.50
     знает
    0.50
    Activations Density 0.000%

    No Known Activations