© 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. 210999
    Prev
    Next
    INDEX
    Explanations

    foreign characters and punctuation

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

    wine label

    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
     +/-
    0.50
     water
    0.49
     Variante
    0.49
     fellow
    0.48
     Huck
    0.46
     Sache
    0.46
     concrete
    0.45
     \<
    0.45
     "
    0.45
     striving
    0.45
    POSITIVE LOGITS
    sieh
    0.51
    分割
    0.50
    Ḩ
    0.49
    Ẹ
    0.48
    Ḥ
    0.47
    THREADS
    0.46
    ꔹ
    0.46
    संबंध
    0.45
    Ки
    0.45
    Сер
    0.45
    Activations Density 0.001%

    No Known Activations