© 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. 76868
    Prev
    Next
    INDEX
    Explanations

    all apps, balance, vaccinations, materials

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

    explicit consent, feels good, commands, index

    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
    olan
    0.45
     रग
    0.44
    क
    0.44
    淙
    0.44
     ®
    0.44
    и
    0.43
    AsString
    0.42
    води
    0.41
    esModule
    0.41
    프
    0.41
    POSITIVE LOGITS
     strategies
    0.54
    städter
    0.51
     hierarchies
    0.48
     hematopoietic
    0.46
     helmets
    0.46
     azimuthal
    0.44
     enhancing
    0.44
     considering
    0.43
    வன்
    0.43
     femmes
    0.43
    Activations Density 0.000%

    No Known Activations