© 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. 49663
    Prev
    Next
    INDEX
    Explanations

    Quartz crystal

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

    luxury goods, specialist procedures, lifelong learning

    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
     τρόπο
    0.52
     niektor
    0.49
     بعض
    0.49
     bepaalde
    0.48
    犮
    0.48
    จริงๆ
    0.47
     ယ
    0.47
     头
    0.47
     будів
    0.47
     σημαν
    0.47
    POSITIVE LOGITS
    p
    0.57
    5
    0.54
    ling
    0.52
    2
    0.50
    died
    0.50
    h
    0.49
    s
    0.48
    der
    0.47
    b
    0.47
    pay
    0.47
    Activations Density 0.000%

    No Known Activations