© 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. 242300
    Prev
    Next
    INDEX
    Explanations

    watch, Maggie, Burton, subtraction, probably thinking

    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
     gestión
    0.50
    )‏
    0.48
     Wetter
    0.45
    how
    0.45
     climate
    0.44
    e
    0.43
    IDI
    0.42
     Hard
    0.41
    india
    0.41
     werde
    0.41
    POSITIVE LOGITS
    想到
    0.47
    三菱
    0.47
    湍
    0.47
     турни
    0.47
    অল
    0.47
    рил
    0.46
    式
    0.45
    椿
    0.45
     Thurston
    0.45
    上市公司
    0.45
    Activations Density 0.001%

    No Known Activations