© 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. 113521
    Prev
    Next
    INDEX
    Explanations

    checking email, setup

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

    turnover, Discord, fashion, languages

    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
     лиц
    0.50
    溂
    0.49
     உயிர
    0.47
     osoba
    0.46
    by
    0.44
     வன
    0.44
     உயிர்
    0.44
     இற
    0.43
     zusätzlich
    0.43
     leisten
    0.43
    POSITIVE LOGITS
    ردو
    0.53
    ण्डे
    0.49
    囍
    0.48
    ◝
    0.47
     वगैरह
    0.45
    CCOCC
    0.45
    JRE
    0.45
    сайт
    0.45
    Visibility
    0.43
    CCOC
    0.43
    Activations Density 0.000%

    No Known Activations