© 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. 154269
    Prev
    Next
    INDEX
    Explanations

    choice but

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

    technical guides or generation

    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
    اعل
    0.54
    关闭
    0.49
    ுடன்
    0.48
    飭
    0.48
    全都
    0.47
    尔多
    0.46
     سوق
    0.45
     preservar
    0.43
     اجر
    0.43
    肠
    0.43
    POSITIVE LOGITS
    Sanchez
    0.51
    Nguyen
    0.47
    ability
    0.46
    Rough
    0.46
     Sanchez
    0.46
     mieux
    0.45
     Nguyen
    0.45
    Autumn
    0.45
     ലേഖ
    0.43
     सेक्सी
    0.43
    Activations Density 0.000%

    No Known Activations