© 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. 51882
    Prev
    Next
    INDEX
    Explanations

    most commonly

    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
     impedir
    0.50
    储存
    0.48
    عتها
    0.45
     wiederum
    0.44
    脍
    0.43
    udere
    0.42
    财务
    0.42
    рят
    0.42
     notions
    0.41
    而后
    0.41
    POSITIVE LOGITS
    ŭ
    0.49
    android
    0.48
     Tanzania
    0.46
     Tent
    0.45
     calf
    0.45
    atanam
    0.45
    トップ
    0.45
     Tanjung
    0.45
    popup
    0.44
     कैल्शियम
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.