© 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. 99462
    Prev
    Next
    INDEX
    Explanations

    both date and time portion

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

    jokes, not stereotypes

    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
     subpoenas
    0.50
     anciennes
    0.48
    changers
    0.46
     reformers
    0.46
     newcomers
    0.45
     remed
    0.45
     যতদিন
    0.44
    帶
    0.44
     insurers
    0.43
     reméd
    0.43
    POSITIVE LOGITS
     обоих
    0.53
    aline
    0.47
    rable
    0.46
    ย์
    0.46
    verbal
    0.46
    Both
    0.45
    orbital
    0.44
     항공
    0.44
    aer
    0.44
    Elapsed
    0.44
    Activations Density 0.000%

    No Known Activations