© 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. 227239
    Prev
    Next
    INDEX
    Explanations

    business, academic, and location names

    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
     paul
    0.51
     ane
    0.47
     vg
    0.47
    </div>
    0.47
     PAUL
    0.45
     ull
    0.43
     aru
    0.42
     순간
    0.42
    ires
    0.42
    一天
    0.41
    POSITIVE LOGITS
    Variance
    0.56
    Concurrency
    0.50
    transactions
    0.49
     discurso
    0.48
    ći
    0.47
    clusters
    0.47
    Qatar
    0.47
    辯
    0.47
    City
    0.46
    cluster
    0.46
    Activations Density 0.000%

    No Known Activations