© 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. 44934
    Prev
    Next
    INDEX
    Explanations

    same equation and production

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

    defining concepts or ideas

    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
     everyone
    0.59
     semua
    0.58
     smartest
    0.54
    і
    0.54
     all
    0.53
     remarkably
    0.52
     plummeted
    0.52
     skyrocketed
    0.52
     exceedingly
    0.51
     everything
    0.50
    POSITIVE LOGITS
     রোগ
    0.55
     或
    0.51
     ከሆነ
    0.50
     করিতেছিল
    0.50
     نیست
    0.48
     专业
    0.47
    ORIENT
    0.47
    Stylesheet
    0.47
    ETTE
    0.47
    Segmentation
    0.47
    Activations Density 0.000%

    No Known Activations