© 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. 184377
    Prev
    Next
    INDEX
    Explanations

    quick analytics and search over time

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

    mathematical descriptions

    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
    )}>
    0.49
    心脏
    0.48
     Tiến
    0.44
    acağım
    0.44
    צוע
    0.44
    ForItem
    0.44
     dört
    0.44
     理解
    0.44
    arsanız
    0.43
     सकुशल
    0.43
    POSITIVE LOGITS
     nupt
    0.49
    ਪ
    0.46
    ਇ
    0.45
    合わせて
    0.44
     aging
    0.44
    ਕ
    0.43
    rounded
    0.43
    changing
    0.43
     teda
    0.42
    ascending
    0.41
    Activations Density 0.000%

    No Known Activations