© 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. 158625
    Prev
    Next
    INDEX
    Explanations

    begin to explore

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

    building or creating LLMs

    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
     อุ
    0.56
     sahip
    0.49
     项
    0.49
     pelea
    0.48
     买
    0.47
     书
    0.47
    >∗</
    0.47
     忄
    0.47
     nieco
    0.46
     儿
    0.46
    POSITIVE LOGITS
     destruct
    0.47
    kept
    0.44
    X
    0.44
    １
    0.44
    펴
    0.43
    continues
    0.43
    l
    0.43
    Бу
    0.42
    detected
    0.42
    郵
    0.42
    Activations Density 0.003%

    No Known Activations