© 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. 129123
    Prev
    Next
    INDEX
    Explanations

    special offers and inclusion

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

    same or similar

    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
    uyorum
    0.47
     જાણ
    0.46
    惊讶
    0.45
     विश्व
    0.43
    VV
    0.43
     समय
    0.43
     ఒక
    0.43
     అన
    0.43
     বাচ্চাদের
    0.43
    POSITIVE LOGITS
     recibió
    0.44
     campaigns
    0.43
     spécialement
    0.43
     promos
    0.42
     incl
    0.42
    是
    0.42
    特
    0.42
    加
    0.42
     wang
    0.41
    在
    0.41
    Activations Density 0.003%

    No Known Activations