© 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. 10-GEMMASCOPE-RES-131K
    7. 84866
    Prev
    Next
    INDEX
    Explanations

    as long as

    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
     but
    -2.52
     only
    -1.50
    はこんな感じ
    -1.45
     навіть
    -1.37
    虽然
    -1.35
    เพราะ
    -1.32
    だったが
    -1.30
     because
    -1.30
     as
    -1.27
     even
    -1.27
    POSITIVE LOGITS
     its
    1.95
     that
    1.76
     первого
    1.49
     gefeiert
    1.48
     vrijdag
    1.43
    olstadt
    1.39
     و
    1.39
     —
    1.38
     pierwszy
    1.37
     belegt
    1.34
    Activations Density 0.019%

    No Known Activations