© 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. 233427
    Prev
    Next
    INDEX
    Explanations

    our own

    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
     liter
    0.53
     pril
    0.50
     चढ
    0.46
     hund
    0.45
     perjalanan
    0.45
    ਦ
    0.45
     próxim
    0.44
    chargez
    0.43
    ंख
    0.42
     tasso
    0.42
    POSITIVE LOGITS
    aceans
    0.49
    IGroup
    0.48
    Cate
    0.47
    ని
    0.45
    Oscar
    0.44
     Christi
    0.44
     организаций
    0.43
    刬
    0.43
    论坛
    0.43
     органами
    0.42
    Activations Density 0.002%

    No Known Activations