© 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. 10-GEMMASCOPE-RES-131K
    7. 43215
    Prev
    Next
    INDEX
    Explanations

    defendants

    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
    When
    -3.13
    Both
    -3.06
    Before
    -2.80
    With
    -2.78
    After
    -2.77
    Taking
    -2.73
    For
    -2.69
    Even
    -2.69
    There
    -2.66
    During
    -2.66
    POSITIVE LOGITS
     unbelievably
    2.48
     they
    2.41
     terrific
    2.33
    🫅
    2.13
     ridiculously
    2.11
    嗵
    2.05
    鲎
    2.05
     AMAZING
    2.02
     insanely
    2.02
     Conſ
    1.99
    Activations Density 0.035%

    No Known Activations