© 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. 32442
    Prev
    Next
    INDEX
    Explanations

    present disclosure specification invention study

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

    presenting academic work or inventions

    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
     कहते
    0.54
    💐
    0.53
    ight
    0.50
    ġ
    0.49
     👉
    0.49
     Dung
    0.48
     dhamma
    0.48
     वजन
    0.47
     ✨
    0.47
    ə
    0.47
    POSITIVE LOGITS
    ш
    0.51
    ش
    0.44
    يك
    0.44
    ین
    0.43
     generaciones
    0.42
    рата
    0.41
     Государ
    0.41
    лями
    0.40
    ват
    0.40
    уз
    0.39
    Activations Density 0.001%

    No Known Activations