© 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. 87487
    Prev
    Next
    INDEX
    Explanations

    development and banking

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

    generated by AI models

    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
     liturgical
    0.61
    is
    0.54
    el
    0.50
     liturg
    0.50
    o
    0.47
    s
    0.47
    gave
    0.47
    il
    0.47
     лига
    0.47
     elution
    0.47
    POSITIVE LOGITS
     نزدیک
    0.52
     développ
    0.51
    农
    0.50
    Crop
    0.49
    銀行
    0.49
     डेवलप
    0.48
    Banking
    0.47
    Developers
    0.47
     svilupp
    0.47
     udvik
    0.47
    Activations Density 0.001%

    No Known Activations