© 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. 40970
    Prev
    Next
    INDEX
    Explanations

    clothing and relationships

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

    material properties or conditions

    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
    ści
    0.50
     ನಿಮಗೆ
    0.46
     ನಿಮ್ಮ
    0.45
     உங்களுக்கு
    0.44
     устройств
    0.44
     পাতার
    0.44
     স্পষ্ট
    0.44
     给
    0.44
    uu
    0.43
    ское
    0.43
    POSITIVE LOGITS
    wives
    0.47
     marriages
    0.46
     prophe
    0.44
    خلص
    0.44
     shod
    0.44
     bosom
    0.43
    コス
    0.43
     ebenso
    0.43
     esposa
    0.42
     modestly
    0.42
    Activations Density 0.000%

    No Known Activations