© 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. 48462
    Prev
    Next
    INDEX
    Explanations

    early life, career, or background

    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
     escritores
    -2.14
     WHICH
    -2.14
     oscuro
    -2.11
    いいですね
    -1.99
     than
    -1.98
     cristianos
    -1.97
     italianos
    -1.96
    韡
    -1.95
     elimina
    -1.95
     hastily
    -1.95
    POSITIVE LOGITS
    These
    2.17
    s
    2.16
    When
    2.13
     sebelum
    2.03
    是
    2.02
    .
    1.95
    lgari
    1.88
     Tentang
    1.86
     Makanan
    1.82
     Before
    1.79
    Activations Density 0.010%

    No Known Activations