© 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. 240830
    Prev
    Next
    INDEX
    Explanations

    personal or company revenue

    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
    裹
    0.52
    放射
    0.51
    會
    0.46
     Kathleen
    0.46
    原
    0.45
     Portable
    0.44
     Solidarity
    0.44
     Rodney
    0.44
     Resident
    0.44
    兢
    0.44
    POSITIVE LOGITS
     оптима
    0.56
    linson
    0.51
     форм
    0.50
    ıc
    0.50
     presento
    0.50
    opis
    0.48
    atürk
    0.48
     знали
    0.48
     компенса
    0.48
     inhomogeneities
    0.48
    Activations Density 0.001%

    No Known Activations