© 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. 136812
    Prev
    Next
    INDEX
    Explanations

    own personal belongings

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

    Linux integration, algorithms, distorted

    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
     ස
    0.57
     आकर्
    0.53
     खेलकर
    0.52
     çıkan
    0.52
     ۲
    0.51
     entertain
    0.50
     ۷
    0.50
    <unused663>
    0.50
     ۵
    0.50
     Waterfall
    0.49
    POSITIVE LOGITS
    σια
    0.47
     memoir
    0.45
     dining
    0.45
    enste
    0.42
     dictionary
    0.41
     heroes
    0.41
     hip
    0.41
     ridge
    0.40
    nete
    0.40
     handheld
    0.40
    Activations Density 0.002%

    No Known Activations