© 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-16K
    7. 12493
    Prev
    Next
    INDEX
    Explanations

    numerical rows

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

    matrix structure

    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_16k_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
     mlijeka
    0.43
     ricotta
    0.43
    odils
    0.43
    nur
    0.43
     Dezember
    0.42
     Jamboree
    0.42
    铒
    0.42
    goatee
    0.41
     telur
    0.41
     SANT
    0.41
    POSITIVE LOGITS
     nonzero
    0.42
     кол
    0.42
     noisy
    0.42
    \_
    0.39
     coll
    0.39
     역시
    0.39
     transmission
    0.39
     ROWS
    0.38
    ψη
    0.38
     कृपया
    0.38
    Activations Density 0.003%

    No Known Activations