© 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. 172633
    Prev
    Next
    INDEX
    Explanations

    distributed over; meals program

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

    attraction, importance, tribal, acknowledging, because, Python

    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
    رات
    0.50
    の両
    0.47
    形態
    0.45
    想要
    0.44
     Abstract
    0.43
    ండి
    0.43
    大
    0.43
    變
    0.43
     RAW
    0.42
    ვლ
    0.42
    POSITIVE LOGITS
    lery
    0.52
     پیغم
    0.52
     вижу
    0.50
     гимна
    0.50
     तिवारी
    0.49
    aż
    0.48
     त्रिपुरा
    0.48
     kua
    0.48
    icu
    0.47
     часов
    0.47
    Activations Density 0.000%

    No Known Activations