© 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. 244909
    Prev
    Next
    INDEX
    Explanations

    star formation, virtual machine, AI, extensive series

    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
     சிறப்பாக
    0.51
    ociaż
    0.47
    rda
    0.46
     বিমানের
    0.45
     ಉತ್ಪ
    0.45
     않습니다
    0.44
     შესაძ
    0.44
     沈
    0.44
     মস
    0.44
     საბ
    0.44
    POSITIVE LOGITS
     commander
    0.50
    commander
    0.50
    вший
    0.49
    ﻞ
    0.46
    ÍA
    0.46
    роят
    0.45
    ประกัน
    0.45
    TON
    0.44
    Portrait
    0.44
    ГИ
    0.43
    Activations Density 0.001%

    No Known Activations