© 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. 126626
    Prev
    Next
    INDEX
    Explanations

    numbers or digits

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

    five in lists

    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
    ne
    1.25
    s
    1.25
    ı
    1.10
    个
    1.09
    li
    1.07
    IS
    1.00
    ž
    0.97
    트
    0.94
    什么
    0.92
     இருந்த
    0.90
    POSITIVE LOGITS
    ’
    1.18
    ↵↵
    1.16
    can
    1.16
    ↵
    1.13
    го
    1.12
    ur
    1.10
    ir
    1.07
    را
    1.07
    να
    1.06
    ил
    1.06
    Activations Density 1.522%

    No Known Activations