© 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. 86292
    Prev
    Next
    INDEX
    Explanations

    foreign words and punctuation

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

    docstring, capacity, spare key

    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
    awać
    0.47
     avoir
    0.46
    दों
    0.43
     urmă
    0.42
     opponent
    0.41
     doub
    0.41
    idered
    0.40
    ও
    0.40
     uttered
    0.40
    łe
    0.40
    POSITIVE LOGITS
    рное
    0.48
     हाश
    0.47
     сервис
    0.46
     garante
    0.46
     Shash
    0.46
     Breaks
    0.44
     جهت
    0.44
    ानुसार
    0.44
     Shu
    0.43
     توسط
    0.43
    Activations Density 0.001%

    No Known Activations