© 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. 190125
    Prev
    Next
    INDEX
    Explanations

    foreign language or script

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

    boost reported profits

    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
     tricks
    0.53
    nél
    0.48
    ných
    0.47
     Tricks
    0.47
    妙
    0.46
    ल
    0.44
    куру
    0.42
    )}-\
    0.42
     पेशेवरों
    0.41
    ্যাল
    0.40
    POSITIVE LOGITS
     رسیده
    0.48
    ."
    0.46
     {(
    0.46
     کە
    0.45
     Gep
    0.44
     Архиви
    0.44
    لمه
    0.44
     cilia
    0.43
    時は
    0.43
     অনুষ্ঠান
    0.43
    Activations Density 0.000%

    No Known Activations