© 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. 202059
    Prev
    Next
    INDEX
    Explanations

    rubber footwear

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

    explaining tissue accuracy mouse

    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
     MINISTRY
    0.55
    色列
    0.53
    お金
    0.51
    MATERIAL
    0.49
     Organizational
    0.49
    सरकारी
    0.48
     Controvers
    0.47
    祢
    0.47
     GOVERNMENT
    0.46
     Министерства
    0.46
    POSITIVE LOGITS
    slug
    0.54
    raised
    0.48
    웜
    0.48
     mele
    0.46
    isateur
    0.45
    strateg
    0.45
    merged
    0.44
    classed
    0.44
    way
    0.44
     mash
    0.44
    Activations Density 0.001%

    No Known Activations