© 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. 96746
    Prev
    Next
    INDEX
    Explanations

    school year admission into Linux kernel

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

    Southern Hemisphere / Australia

    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
    к
    0.50
     सॉल्यूशन
    0.43
     повністю
    0.43
    atoon
    0.43
    cystic
    0.43
    .
    0.42
    клары
    0.42
    ências
    0.42
    Л
    0.42
     கருவ
    0.41
    POSITIVE LOGITS
    roffen
    0.44
    เผ
    0.44
     vib
    0.42
    ويم
    0.41
     fud
    0.41
     وصحبه
    0.39
    Debugger
    0.38
     swung
    0.38
     follower
    0.38
    ानुसार
    0.38
    Activations Density 0.001%

    No Known Activations