© 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. 7049
    Prev
    Next
    INDEX
    Explanations

    protecting or acting effectively

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

    large, complex, emerging

    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
     wears
    0.59
     shops
    0.56
     بطولة
    0.54
     pacif
    0.53
     कॉलेज
    0.52
     Piero
    0.52
     শাসক
    0.51
     モ
    0.51
     Peut
    0.51
     टीचर्स
    0.50
    POSITIVE LOGITS
    pronged
    0.57
    position
    0.50
    <0x80>
    0.49
    itized
    0.49
    grained
    0.47
    вна
    0.47
    visual
    0.47
    blown
    0.47
    terminated
    0.46
    s
    0.46
    Activations Density 0.000%

    No Known Activations