© 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. 156714
    Prev
    Next
    INDEX
    Explanations

    serving into, collection act, hear of, kick to, said they, Air Force

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

    incite hatred or subtle way

    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
    *
    0.61
    leading
    0.50
    la
    0.49
    m
    0.48
    a
    0.48
    cur
    0.48
    n
    0.48
    l
    0.47
    ay
    0.47
    0
    0.47
    POSITIVE LOGITS
    інки
    0.57
     campes
    0.55
     diğer
    0.54
     excepciones
    0.52
    طرف
    0.50
    قیه
    0.50
     دیگری
    0.50
     والے
    0.49
     ሌሎች
    0.49
     لهم
    0.49
    Activations Density 0.000%

    No Known Activations