© 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. 111156
    Prev
    Next
    INDEX
    Explanations

    manufacturing, products, or services

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

    return result, send them, mobile app

    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
    in
    0.49
    ใน
    0.48
     वोल्टेज
    0.46
     چال
    0.46
     הי
    0.46
    ช
    0.46
    ophysical
    0.45
     শক্তির
    0.44
    ப
    0.44
     ngo
    0.43
    POSITIVE LOGITS
     vorhand
    0.47
    тив
    0.47
     confuses
    0.47
    rā
    0.46
    ابية
    0.46
     Também
    0.46
     Küche
    0.45
    texto
    0.44
     complexe
    0.43
     was
    0.43
    Activations Density 0.001%

    No Known Activations