© 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. 86563
    Prev
    Next
    INDEX
    Explanations

    place an order

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

    academic and professional contexts

    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
     is
    0.53
     siden
    0.51
     vigor
    0.51
    -
    0.48
     morbid
    0.47
     more
    0.46
     information
    0.46
    information
    0.46
     wohn
    0.46
     abomin
    0.46
    POSITIVE LOGITS
    醃
    0.52
    可以使用
    0.48
     दुश्
    0.47
    দু
    0.46
    鏤
    0.46
    itabbam
    0.45
    atthena
    0.45
     стрельца
    0.45
    τηση
    0.43
    บูร
    0.43
    Activations Density 0.001%

    No Known Activations