© 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. 80276
    Prev
    Next
    INDEX
    Explanations

    additional upholstery or interior

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

    SUV, Man, K, Air, romantic

    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
    лити
    0.47
     Віль
    0.46
    和田
    0.46
    秘书
    0.45
    孀
    0.45
     Ismail
    0.45
    סטר
    0.45
    スムーズ
    0.45
    عمال
    0.45
    نامج
    0.44
    POSITIVE LOGITS
    in
    0.63
    ah
    0.63
    ul
    0.60
    e
    0.57
    le
    0.56
    U
    0.55
    on
    0.55
    uh
    0.54
    ue
    0.53
    ep
    0.52
    Activations Density 0.000%

    No Known Activations