© 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. 194319
    Prev
    Next
    INDEX
    Explanations

    top right corner

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

    HTML headings and form structures

    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
    bg
    0.45
     bg
    0.43
     remembered
    0.43
     rgba
    0.42
    backgroundImage
    0.41
     soundtrack
    0.41
    国
    0.41
    mousemove
    0.40
     Academy
    0.40
     outer
    0.40
    POSITIVE LOGITS
    কোত্তর
    0.49
     REACTORS
    0.46
     undocumented
    0.45
    म्प्ट
    0.43
     diagnóstico
    0.43
     stwier
    0.43
    EXPORT
    0.43
     criteri
    0.43
    🩺
    0.43
     URANIUM
    0.42
    Activations Density 0.001%

    No Known Activations