© 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. 2824
    Prev
    Next
    INDEX
    Explanations

    news reporting and events

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

    news from governments and organizations

    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
     위하여
    0.53
    和谐
    0.52
     을
    0.52
    Macro
    0.52
     값을
    0.50
    Literature
    0.50
     سنة
    0.49
    𝑃
    0.48
    珽
    0.48
    Distribution
    0.48
    POSITIVE LOGITS
     Reuters
    0.85
     tweeted
    0.79
     AFP
    0.77
     Biden
    0.75
    Reuters
    0.72
     शुक्रवार
    0.69
     বৃহস্পতিবার
    0.68
     রোববার
    0.67
     बृहस्पतिवार
    0.65
     Thursday
    0.64
    Activations Density 0.055%

    No Known Activations