© 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. 210778
    Prev
    Next
    INDEX
    Explanations

    state crisis entrances HANDLE collected

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

    applied voltage or increasing incidence

    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
     User
    0.54
     user
    0.52
    User
    0.50
    í
    0.48
     and
    0.48
     Lagi
    0.47
     eta
    0.47
     Network
    0.46
     again
    0.46
     Et
    0.46
    POSITIVE LOGITS
    Sholes
    0.53
     TRANSPORTURI
    0.53
    <unused35>
    0.48
     carbohydrates
    0.48
    ковые
    0.46
     ವಿಧಾನಸ
    0.46
    सिस
    0.45
     déprimées
    0.45
    टीसी
    0.45
    <unused3>
    0.44
    Activations Density 0.001%

    No Known Activations