© 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. 177338
    Prev
    Next
    INDEX
    Explanations

    animal balloons

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

    list item markers

    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
    ாய்ச்சி
    0.51
    自由
    0.48
     Verhalten
    0.48
    保有
    0.46
     ziek
    0.46
    ことがある
    0.46
    ล
    0.46
     fortfarande
    0.45
    А
    0.45
    <0x96>
    0.44
    POSITIVE LOGITS
    ikul
    0.51
    rime
    0.48
    lew
    0.46
    nergy
    0.46
    qat
    0.45
    ud
    0.45
     δὲ
    0.45
    wała
    0.45
     첫
    0.45
    wa
    0.44
    Activations Density 0.002%

    No Known Activations