© 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. 42120
    Prev
    Next
    INDEX
    Explanations

    earnest and Ernest

    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
    ⢊
    -2.89
     AppCompatTheme
    -2.66
     vanguardia
    -2.61
    ра
    -2.56
     ouvido
    -2.44
     responsables
    -2.36
     pequena
    -2.33
    苤
    -2.33
    følge
    -2.27
     rostros
    -2.27
    POSITIVE LOGITS
    This
    3.00
    1
    2.98
    $
    2.83
    ),
    2.81
    not
    2.77
    8
    2.73
    6
    2.70
    that
    2.70
    s
    2.56
    7
    2.44
    Activations Density 0.004%

    No Known Activations