© 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. 200058
    Prev
    Next
    INDEX
    Explanations

    download or purchase information

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

    not down

    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
    uart
    0.48
    只有
    0.44
    Y
    0.42
    quit
    0.42
    HOL
    0.41
    Only
    0.41
    三年
    0.41
    qd
    0.40
    W
    0.40
     yester
    0.40
    POSITIVE LOGITS
     çeşitli
    0.56
     composants
    0.51
     elektromagnet
    0.50
     komple
    0.47
     bilgiler
    0.46
     bilim
    0.46
    larını
    0.44
    𒋫
    0.43
     தாம்
    0.43
    strukt
    0.43
    Activations Density 0.004%

    No Known Activations