© 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. 14814
    Prev
    Next
    INDEX
    Explanations

    US states and locations

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

    computation graph, friendship, grand

    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
     செல்லும்
    0.49
    uzzo
    0.48
     सोसाइटी
    0.48
     ইলেক্ট্রোলাই
    0.48
     mondiale
    0.47
     sạch
    0.47
    FileOutput
    0.47
    珬
    0.47
     ইলেক্ট
    0.47
    চা
    0.47
    POSITIVE LOGITS
    0.53
     im
    0.48
     Baldwin
    0.45
     appealing
    0.44
     Nick
    0.43
    <0xE3>
    0.41
     ornate
    0.41
    指
    0.41
    toFixed
    0.41
     Opening
    0.40
    Activations Density 0.000%

    No Known Activations