© 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. 216650
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

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

    pasta, analysis, finality, recency

    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
     as
    0.51
    and
    0.49
    벤
    0.49
    맡
    0.49
    vay
    0.48
    pallet
    0.48
     fête
    0.48
    nder
    0.47
    eterm
    0.47
    eping
    0.47
    POSITIVE LOGITS
     最后
    0.54
     Интере
    0.54
     よく
    0.53
     эволю
    0.51
     оконча
    0.50
     一般
    0.50
     最
    0.48
     ткани
    0.48
     ሲ
    0.47
     trasc
    0.47
    Activations Density 0.000%

    No Known Activations