© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130545
    Prev
    Next
    INDEX
    Explanations

    dates with slashes

    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_10/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
     seleccionamos
    -1.30
    âche
    -1.30
    ]:
    -1.27
    窥
    -1.20
    rscheinlich
    -1.14
    ViewStyle
    -1.14
     folgende
    -1.13
     wła
    -1.13
     personaggi
    -1.13
    dyr
    -1.12
    POSITIVE LOGITS
     that
    1.87
     of
    1.62
    4
    1.26
    '
    1.25
    2
    1.23
    CIUDAD
    1.23
    on
    1.22
    5
    1.22
    7
    1.16
     terakhir
    1.16
    Activations Density 0.042%

    No Known Activations