© 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. 177506
    Prev
    Next
    INDEX
    Explanations

    tracking, categories, products

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

    security, identity, host, search

    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
    с
    0.51
    ят
    0.50
     tw
    0.50
    0.48
    о
    0.48
    有的
    0.47
     т
    0.46
    г
    0.46
    YE
    0.45
    и
    0.45
    POSITIVE LOGITS
    ச்சர்
    0.51
     నమోదు
    0.51
     Máy
    0.49
    স্পতিবার
    0.48
    ፕሮ
    0.46
     பாதிக்க
    0.45
    ।]
    0.45
     लैपटॉप
    0.45
    ச்சியை
    0.45
    apo
    0.44
    Activations Density 0.001%

    No Known Activations