© 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. 245683
    Prev
    Next
    INDEX
    Explanations

    veterinarian practice cats contrary mouth date brings

    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
    3
    0.52
    bbs
    0.49
     Prz
    0.49
    lll
    0.47
    bbb
    0.47
    rz
    0.47
    bz
    0.47
     plazas
    0.47
    Пла
    0.47
     alde
    0.46
    POSITIVE LOGITS
     entice
    0.48
    箸
    0.47
    ﻊ
    0.46
    ທີ່ມີ
    0.45
     superhuman
    0.44
     पारी
    0.43
    པ་
    0.43
    कर्षण
    0.43
     सम्मेलन
    0.43
     میراتھن
    0.43
    Activations Density 0.000%

    No Known Activations