© 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. 122422
    Prev
    Next
    INDEX
    Explanations

    week with, save waste, she opens, your trust

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

    analyze data

    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
     trophic
    0.58
    لر
    0.50
     秋
    0.50
     Quit
    0.49
     Vote
    0.48
     Constructors
    0.48
     qi
    0.47
     recruited
    0.47
     شو
    0.46
     Procedure
    0.46
    POSITIVE LOGITS
    Jakarta
    0.56
    Bien
    0.53
    "});
    0.52
    Hall
    0.52
    Linkedin
    0.52
    Neben
    0.52
    Hub
    0.50
    Frontend
    0.49
    Seit
    0.49
    carouselExample
    0.48
    Activations Density 0.000%

    No Known Activations