© 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. 177112
    Prev
    Next
    INDEX
    Explanations

    legal and opinionated discourse

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

    AI generated or related content

    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
     nomenclatura
    0.57
     वर्गी
    0.55
     abat
    0.54
    дото
    0.49
     exposition
    0.49
     ước
    0.48
     scompar
    0.48
    𝓀
    0.47
     extrait
    0.47
     ứng
    0.46
    POSITIVE LOGITS
     Croatian
    0.48
     Sleep
    0.44
    imdb
    0.44
     Civil
    0.44
    php
    0.43
     Light
    0.43
    chen
    0.43
    id
    0.42
    andran
    0.42
     Serbian
    0.42
    Activations Density 0.000%

    No Known Activations