© 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. 21657
    Prev
    Next
    INDEX
    Explanations

    fixed income, company names, brands

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

    specific programming library 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
    determined
    0.52
    ↵↵
    0.44
    information
    0.43
    性と
    0.43
    nets
    0.42
    ports
    0.42
    assertions
    0.42
    certification
    0.42
     Polarization
    0.42
    sil
    0.41
    POSITIVE LOGITS
     rémun
    0.45
     partnered
    0.43
    띵
    0.43
     veggie
    0.42
    យើង
    0.42
    ئيه
    0.41
     résident
    0.41
     iniciativas
    0.41
     passcode
    0.41
     sostenibilidad
    0.41
    Activations Density 0.000%

    No Known Activations