© 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. 124126
    Prev
    Next
    INDEX
    Explanations

    piece of, musical Chess, first before

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

    speech recognition, Synchronization, json

    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
    ن
    0.60
    if
    0.47
     for
    0.45
    نن
    0.45
    une
    0.43
    ช่วง
    0.43
    न
    0.43
    n
    0.42
    for
    0.42
    told
    0.42
    POSITIVE LOGITS
    醯
    0.45
    <unused14>
    0.45
     vacancies
    0.43
     stör
    0.43
     reservation
    0.43
     acet
    0.42
    attamente
    0.42
     amortization
    0.42
    caya
    0.41
    ស្រ
    0.41
    Activations Density 0.000%

    No Known Activations