© 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. 49679
    Prev
    Next
    INDEX
    Explanations

    when i

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

    outputs, prints, writes

    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
     ကျွန်
    0.52
     環
    0.51
     FIRST
    0.50
     propio
    0.49
     vicepresidente
    0.48
    熾
    0.48
    謗
    0.48
     特許
    0.48
     多く
    0.47
     KIDS
    0.46
    POSITIVE LOGITS
    have
    0.54
    Generate
    0.52
    Feels
    0.48
    generate
    0.48
    Internet
    0.47
    Forecast
    0.46
    Tap
    0.46
    in
    0.45
    Have
    0.45
    Queue
    0.45
    Activations Density 0.000%

    No Known Activations