© 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. 250870
    Prev
    Next
    INDEX
    Explanations

    gas station or disease

    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
    自从
    0.48
     Contributing
    0.46
     Pierws
    0.45
     Depuis
    0.45
     aspekt
    0.45
     Claims
    0.44
    듑
    0.44
    깅
    0.44
     mukaan
    0.43
    चलर्स
    0.43
    POSITIVE LOGITS
     cambia
    0.47
     пен
    0.47
     ос
    0.46
    LaunchAction
    0.45
     cranes
    0.45
     להת
    0.45
     ס
    0.43
     сына
    0.43
     eigent
    0.43
     كامل
    0.43
    Activations Density 0.000%

    No Known Activations