© 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. 106722
    Prev
    Next
    INDEX
    Explanations

    excessively short

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

    resetting devices, compiling code, numbers

    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
     intér
    0.55
     HOMO
    0.52
     塩
    0.51
     înt
    0.50
     vér
    0.49
     rén
    0.49
     suffit
    0.49
     fécond
    0.48
     extrem
    0.47
     intends
    0.47
    POSITIVE LOGITS
    其他
    0.54
    还是
    0.48
    <0xE3>
    0.45
    어도
    0.44
    ফর
    0.44
    导航
    0.44
    数据
    0.44
    يا
    0.43
    或其他
    0.43
    र्ड
    0.43
    Activations Density 0.000%

    No Known Activations