© 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. 65040
    Prev
    Next
    INDEX
    Explanations

    marketing and research professions

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

    Extreme saturation and mergers

    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
    ร้อง
    0.47
    ؘ
    0.46
    
    0.45
     ഏറ്റവും
    0.43
    )){
    0.42
    ぐるみ
    0.42
    Underv
    0.40
    ingen
    0.40
     गर्लफ्रेंड
    0.40
    🕹
    0.40
    POSITIVE LOGITS
    unet
    0.47
     continuamos
    0.46
     Серге
    0.46
    icron
    0.46
    āta
    0.46
     χρει
    0.45
     requieren
    0.45
    films
    0.44
    inheritDoc
    0.44
    দ্ম
    0.44
    Activations Density 0.000%

    No Known Activations