© 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. 103994
    Prev
    Next
    INDEX
    Explanations

    continue grilling

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

    refine settings and positioning

    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
     anteriores
    0.49
     dijual
    0.49
    previous
    0.44
    詬
    0.43
     shirts
    0.41
     vendidos
    0.41
     gowns
    0.41
     hogares
    0.40
     rentals
    0.40
     supermarkets
    0.39
    POSITIVE LOGITS
     astrophys
    0.49
     AIAA
    0.44
    纳米
    0.44
    ignée
    0.43
     опу
    0.42
    矍
    0.41
     மந்திர
    0.40
     διε
    0.40
     جناب
    0.40
     unserer
    0.39
    Activations Density 0.001%

    No Known Activations