© 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. 105894
    Prev
    Next
    INDEX
    Explanations

    browser contexts

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

    web browser developer tools

    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
    Replace
    0.54
    مس
    0.54
    replace
    0.50
    region
    0.49
    اون
    0.49
    اؤ
    0.48
    args
    0.48
    s
    0.48
    red
    0.47
    rev
    0.46
    POSITIVE LOGITS
    ä
    0.60
     शुभेच्छा
    0.58
     ActionListener
    0.56
     मृतक
    0.56
     掛
    0.54
    बित
    0.54
     퇴
    0.53
    ગ
    0.52
     หยุด
    0.52
    डी
    0.52
    Activations Density 0.005%

    No Known Activations