© 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. 45640
    Prev
    Next
    INDEX
    Explanations

    its charity

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

    baking cookies

    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
     уме
    0.52
    FormParams
    0.52
    住所
    0.50
    狯
    0.50
     обосно
    0.49
     द्विवेदी
    0.49
     Concepción
    0.48
    мана
    0.48
     جوړونکو
    0.48
     хто
    0.48
    POSITIVE LOGITS
     )
    0.46
    িয়৷
    0.41
     nails
    0.41
        
    0.40
    \,
    0.40
     cyt
    0.39
     electrons
    0.39
     irrigation
    0.39
     sewing
    0.39
     sidelines
    0.39
    Activations Density 0.000%

    No Known Activations