© 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. 80540
    Prev
    Next
    INDEX
    Explanations

    helmet tv talent performed

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

    numbers, styles, units

    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
     verantwort
    0.48
     saranam
    0.48
     planner
    0.47
     hü
    0.46
     planners
    0.45
     itineraries
    0.45
    蹰
    0.45
     lakini
    0.44
     педаго
    0.44
     baina
    0.44
    POSITIVE LOGITS
     Mocha
    0.43
    quired
    0.42
    ようやく
    0.41
    cimentos
    0.41
    barrels
    0.41
     thí
    0.40
     industrialized
    0.39
    莢
    0.39
     형성
    0.39
     Thames
    0.39
    Activations Density 0.001%

    No Known Activations