© 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. 21809
    Prev
    Next
    INDEX
    Explanations

    multilingual signs and indicators

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

    this disclaimer at the end

    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
     तलब
    0.41
    managers
    0.39
     offences
    0.39
     twine
    0.38
    sendCommand
    0.38
     _{\
    0.38
     dataSource
    0.38
     offending
    0.38
     {{\
    0.38
     deprive
    0.37
    POSITIVE LOGITS
    我們
    0.54
    你們
    0.53
    স্ট্র
    0.53
     Convertible
    0.45
    หรือ
    0.44
    咱們
    0.43
     لدينا
    0.43
     changement
    0.43
     Adoption
    0.43
    我们
    0.42
    Activations Density 0.000%

    No Known Activations