© 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. 155711
    Prev
    Next
    INDEX
    Explanations

    cookie is a text file

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

    need precise

    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
     saddhim
    0.51
     dhammo
    0.49
     dukkham
    0.49
     ≠
    0.49
    INCREMENT
    0.48
     চুপ
    0.47
     attham
    0.46
     Colombe
    0.46
    CHUNK
    0.46
     കൂടി
    0.45
    POSITIVE LOGITS
    ულის
    0.50
    צ
    0.49
    ულ
    0.46
     advancement
    0.46
    Adv
    0.45
    되었다
    0.45
    า
    0.45
    وتی
    0.45
     Adv
    0.44
    ى
    0.44
    Activations Density 0.000%

    No Known Activations