© 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. 133732
    Prev
    Next
    INDEX
    Explanations

    years, months, weeks, days

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

    numbers, dates, and durations

    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
    ান্ত্রিক
    0.44
    不同的
    0.41
     millió
    0.41
    পরিচিত
    0.41
     Після
    0.41
    Cyber
    0.40
    Pars
    0.40
    𝙋
    0.40
     সম্প্রতি
    0.39
     উপলক্ষে
    0.39
    POSITIVE LOGITS
     nine
    0.53
     neun
    0.51
     eighteen
    0.47
     !
    0.45
     nearly
    0.45
     nin
    0.44
     eight
    0.41
    nine
    0.41
     eleven
    0.40
     thirteen
    0.40
    Activations Density 0.025%

    No Known Activations