© 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. 163719
    Prev
    Next
    INDEX
    Explanations

    Interior trim

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

    **

    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
     unterscheiden
    0.47
    😣
    0.45
    🏛
    0.44
    政
    0.41
    🤴
    0.41
     misunder
    0.41
    /${
    0.40
    学的
    0.40
    🤧
    0.40
    ทำงาน
    0.39
    POSITIVE LOGITS
     Exterior
    0.53
    pictured
    0.52
    chromed
    0.50
     slotted
    0.49
     Fiberglass
    0.49
    centering
    0.49
     Cabrio
    0.49
     Remo
    0.49
     सूर्
    0.48
     ferrite
    0.48
    Activations Density 0.002%

    No Known Activations