© 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. 202840
    Prev
    Next
    INDEX
    Explanations

    noun followed by verb

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

    defining or explaining situations

    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
     सके
    0.45
    ábado
    0.44
    ៏
    0.44
    ту
    0.43
    --------------
    0.43
     あれ
    0.42
     погиб
    0.41
     asymmetries
    0.41
     изобра
    0.41
    }\}
    0.41
    POSITIVE LOGITS
     eBay
    0.49
     seaport
    0.45
     prepayment
    0.44
    Xr
    0.44
     oferty
    0.43
     oprac
    0.43
     matrim
    0.42
    MySQL
    0.42
     Seagate
    0.42
    eBay
    0.42
    Activations Density 0.001%

    No Known Activations