© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71970
    Prev
    Next
    INDEX
    Explanations

    navigation keys

    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
     vė
    -1.15
    ̴
    -1.12
    ність
    -1.09
     senere
    -1.03
    tismo
    -1.03
    ologous
    -1.02
    álise
    -1.01
    aconda
    -0.98
    Datuak
    -0.97
    ovich
    -0.97
    POSITIVE LOGITS
     either
    1.23
     umgangssprach
    1.00
    rugu
    0.97
    ဦ
    0.96
    madeus
    0.96
     dirigente
    0.96
    Studi
    0.94
    romatic
    0.94
    Bereich
    0.94
    either
    0.92
    Activations Density 0.006%

    No Known Activations