© 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. 60944
    Prev
    Next
    INDEX
    Explanations

    illustrate, understand, new

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

    humorous content or lists

    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
     Их
    0.50
     іх
    0.50
     他们
    0.49
     Mereka
    0.48
     Иң
    0.47
     Consequently
    0.46
     Sare
    0.45
    {``
    0.43
     ছাপ
    0.42
    ட்சத்திர
    0.42
    POSITIVE LOGITS
     hyp
    0.52
     हजारों
    0.50
     hypo
    0.47
    ريع
    0.45
    ру
    0.45
    říve
    0.45
     fast
    0.45
     restrictive
    0.45
     restriction
    0.45
     shortage
    0.44
    Activations Density 0.000%

    No Known Activations