© 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. 169539
    Prev
    Next
    INDEX
    Explanations

    parentheses with numbers and punctuation

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

    books and publishers

    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
    automate
    0.46
    MaskInto
    0.42
    पश्चिम
    0.40
     Automation
    0.39
    Periph
    0.39
    encode
    0.38
    scrib
    0.38
    ৤
    0.37
     Veloc
    0.37
     Semaphore
    0.37
    POSITIVE LOGITS
    ẵn
    0.42
     alph
    0.39
     chuy
    0.39
     ánh
    0.39
     sau
    0.39
     小
    0.38
     buk
    0.38
     胸
    0.38
     mait
    0.38
     saber
    0.38
    Activations Density 0.009%

    No Known Activations