© 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. 126657
    Prev
    Next
    INDEX
    Explanations

    people themselves, totally changed

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

    operating system of life

    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
    wege
    0.55
     ننوت
    0.50
     〈
    0.49
    <bbox>
    0.48
     அதிசயங்கள்
    0.47
     Lithuan
    0.47
     celebratory
    0.47
     `<`,
    0.46
     समापन
    0.45
     Xinhua
    0.45
    POSITIVE LOGITS
    iar
    0.51
     you
    0.50
    你
    0.50
    IO
    0.49
    ла
    0.47
    Само
    0.47
    ction
    0.47
    BU
    0.47
    you
    0.46
    йт
    0.46
    Activations Density 0.000%

    No Known Activations