© 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. 74088
    Prev
    Next
    INDEX
    Explanations

    time and position comparisons

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

    quantifiable metrics or states

    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
     অল্প
    0.48
    いろいろ
    0.48
    тено
    0.47
    几种
    0.47
    ərbay
    0.46
     zelo
    0.46
    更多
    0.46
    <?>
    0.45
     কয়েকটি
    0.45
     skupiny
    0.45
    POSITIVE LOGITS
     (!)
    0.54
    niak
    0.49
    ).
    0.46
    (!)
    0.45
     aproximadamente
    0.44
     apiece
    0.43
    বিশিষ্ট
    0.43
     (
    0.42
    ),
    0.41
    +.
    0.41
    Activations Density 0.177%

    No Known Activations