© 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. 88344
    Prev
    Next
    INDEX
    Explanations

    may focus, spend more

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

    breakdown year options

    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
     lý
    0.50
     ferrugine
    0.48
     نحل
    0.47
     nhập
    0.46
     evicted
    0.45
     inhaled
    0.45
    㧕
    0.44
     captivated
    0.44
     ሂደት
    0.44
     vời
    0.43
    POSITIVE LOGITS
    nov
    0.56
    Nov
    0.52
    Serbia
    0.49
    Mass
    0.48
    Tennis
    0.48
    PPP
    0.47
    Pm
    0.47
    斯
    0.46
    innen
    0.46
    娉
    0.46
    Activations Density 0.000%

    No Known Activations