© 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. 146314
    Prev
    Next
    INDEX
    Explanations

    articles from a company

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

    Generation, design, and understanding

    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
    $
    0.54
     إضافة
    0.52
    źć
    0.50
     জিৎ
    0.48
    ća
    0.47
     sluč
    0.46
    ّة
    0.46
    د
    0.46
    ścia
    0.46
     nieuw
    0.46
    POSITIVE LOGITS
    на
    0.49
    मूर्ति
    0.47
    пикир
    0.47
    ্যেষ্ঠ
    0.47
    ным
    0.45
    磯
    0.44
     loosening
    0.44
    omes
    0.43
     electron
    0.42
    ನೇ
    0.41
    Activations Density 0.000%

    No Known Activations