© 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. 165896
    Prev
    Next
    INDEX
    Explanations

    additional supplements or damages

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

    across multiple locations/servers

    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
    عي
    0.52
    各式
    0.51
    parvec
    0.50
     Opfer
    0.49
    分析
    0.48
    最新
    0.47
    瀆
    0.46
     OJ
    0.46
     rmse
    0.46
    BDT
    0.46
    POSITIVE LOGITS
     windscreen
    0.48
    raya
    0.48
    enangan
    0.47
    yam
    0.45
     dalej
    0.45
     herald
    0.44
     properties
    0.44
     역사
    0.44
    am
    0.44
     awn
    0.44
    Activations Density 0.000%

    No Known Activations