© 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. 45046
    Prev
    Next
    INDEX
    Explanations

    Moon, Sun, New Moon

    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
     બાળકો
    0.52
    ร
    0.48
    ก็จะ
    0.48
    शक
    0.47
    ถ้า
    0.46
     पढ़िए
    0.46
    耄
    0.46
     کودک
    0.45
     குழந்தைகள்
    0.45
    ര്‍ക്കും
    0.44
    POSITIVE LOGITS
     (
    0.66
     ((
    0.54
     achieves
    0.50
    -(
    0.49
     BOR
    0.48
     POS
    0.47
     achieving
    0.47
     [
    0.47
     -(
    0.47
     OVER
    0.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.