© 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. 240338
    Prev
    Next
    INDEX
    Explanations

    free and unlimited offers

    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
     ketentuan
    0.54
     tunique
    0.51
    рующий
    0.50
     বজায়
    0.49
    籙
    0.49
    akkhanam
    0.48
    ູນ
    0.48
    <unused22>
    0.48
    avacanam
    0.48
    ர்ப்பு
    0.47
    POSITIVE LOGITS
     immerse
    0.57
     elevate
    0.50
     o
    0.49
     each
    0.49
     a
    0.48
     disperse
    0.47
     la
    0.47
     fire
    0.46
     immers
    0.46
     broad
    0.46
    Activations Density 0.000%

    No Known Activations