© 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. 233084
    Prev
    Next
    INDEX
    Explanations

    business and consumer terms

    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
     아니다
    0.48
     مستوى
    0.47
    晃
    0.47
     භ
    0.47
     جلسه
    0.47
    下
    0.46
     في
    0.46
    dalam
    0.46
    회
    0.45
     就
    0.45
    POSITIVE LOGITS
     pengetahuan
    0.54
     sovi
    0.50
     muitas
    0.48
     Futur
    0.47
     przez
    0.46
     Syri
    0.46
     lin
    0.45
     marít
    0.45
     pertenc
    0.45
     Transformations
    0.44
    Activations Density 0.000%

    No Known Activations