© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 203996
    Prev
    Next
    INDEX
    Explanations

    stencil graffiti and band leader

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

    comparative or quantitative descriptors

    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
     سایټ
    0.57
    <unused1049>
    0.54
    ᚨ
    0.52
     سپورټ
    0.51
     клави
    0.50
     muque
    0.50
     ника
    0.49
     Кі
    0.48
     Zamora
    0.48
    GLIGENCE
    0.48
    POSITIVE LOGITS
    most
    0.62
    ht
    0.57
    sti
    0.53
    it
    0.52
    ş
    0.52
    right
    0.52
    ar
    0.51
    emt
    0.51
    ain
    0.51
    main
    0.49
    Activations Density 0.000%

    No Known Activations