© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 249097
    Prev
    Next
    INDEX
    Explanations

    exception of, public demonstrations, click on, cases an, higher education, represent

    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
     perspiciatis
    0.53
     menyiapkan
    0.52
     failings
    0.48
    を実現
    0.48
     ხელისუფ
    0.47
    <unused41>
    0.46
     хірур
    0.45
     протягом
    0.45
     hopelessness
    0.45
     شکایت
    0.44
    POSITIVE LOGITS
    C
    0.72
    O
    0.61
    R
    0.59
    B
    0.58
    Border
    0.57
    Blood
    0.57
    J
    0.57
    A
    0.55
    Con
    0.54
    Post
    0.54
    Activations Density 0.000%

    No Known Activations