© 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. 129269
    Prev
    Next
    INDEX
    Explanations

    sides of the same coin

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

    common phrases and compound words

    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
     ۲۰
    0.52
     US
    0.51
     FOD
    0.50
     ۷
    0.49
     December
    0.48
     November
    0.48
     USS
    0.47
     October
    0.46
     USA
    0.46
    ä
    0.46
    POSITIVE LOGITS
    級
    0.48
    經驗
    0.47
    治安
    0.46
    天氣
    0.45
    會
    0.44
    ဉ
    0.44
    त्म
    0.43
    经验
    0.43
    ائد
    0.42
    реи
    0.42
    Activations Density 0.001%

    No Known Activations