© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64822
    Prev
    Next
    INDEX
    Explanations

    UI component wrappers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     from
    -1.26
     that
    -1.13
     its
    -1.03
    arranty
    -0.99
     even
    -0.98
     ότι
    -0.97
    :
    -0.94
     to
    -0.92
     Hauptstadt
    -0.92
    atest
    -0.90
    POSITIVE LOGITS
    Ін
    1.20
     morire
    1.16
    ждый
    1.09
    acije
    1.02
    UMBIA
    1.02
     sensazione
    1.02
    广大
    1.00
    lós
    1.00
    Зміст
    0.99
    ykjav
    0.98
    Activations Density 0.002%

    No Known Activations