© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 54514
    Prev
    Next
    INDEX
    Explanations

    interactive election cinema companion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     redist
    0.55
    ger
    0.50
     Redist
    0.48
     ger
    0.46
     redraw
    0.42
     =>{
    0.41
    redraw
    0.41
     丿
    0.40
    Ger
    0.39
    uspended
    0.39
    POSITIVE LOGITS
     interactive
    0.44
     mix
    0.43
     em
    0.42
     Dinosaur
    0.41
    璈
    0.40
    嘶
    0.40
     Humber
    0.39
     conversation
    0.39
     dinosaur
    0.39
     انقلاب
    0.39
    Activations Density 0.006%

    No Known Activations