© 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. 115898
    Prev
    Next
    INDEX
    Explanations

    days of the week

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

    when or where

    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
    罕
    0.47
     주장
    0.45
     raref
    0.45
    óln
    0.42
     debilit
    0.42
     analyzes
    0.42
     aggress
    0.42
    崇
    0.42
     progn
    0.40
     przypad
    0.40
    POSITIVE LOGITS
     tambien
    0.46
     semoga
    0.46
    妺
    0.46
     Kemudian
    0.45
     kemarin
    0.45
     sabato
    0.45
     bottling
    0.44
     domani
    0.44
     завтра
    0.44
     कारखाना
    0.44
    Activations Density 0.001%

    No Known Activations