© 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. 20538
    Prev
    Next
    INDEX
    Explanations

    statistical summary of metrics

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

    average and median values

    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
     averaging
    0.71
     averaged
    0.68
     in
    0.64
     S
    0.64
     averages
    0.62
     moyenne
    0.62
     average
    0.61
     A
    0.59
     )
    0.59
     AVERAGE
    0.59
    POSITIVE LOGITS
     동시에
    0.54
    ő
    0.52
    最初に
    0.51
    žad
    0.50
    contentText
    0.48
    agno
    0.48
    érios
    0.48
    要知道
    0.48
    зне
    0.47
    äub
    0.47
    Activations Density 0.012%

    No Known Activations