© 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. 42
    Prev
    Next
    INDEX
    Explanations

    address is, surname is, listed for

    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
    -1.82
     When
    -1.56
     those
    -1.55
     these
    -1.49
    ників
    -1.48
     because
    -1.35
     ketika
    -1.31
    </h1>
    -1.30
     an
    -1.30
    </h2>
    -1.27
    POSITIVE LOGITS
     chociaż
    1.40
     nieuwe
    1.36
    нового
    1.34
     SUCH
    1.30
    
    1.29
    asnya
    1.28
     choć
    1.24
    逦
    1.24
     neumáticos
    1.23
    喊道
    1.23
    Activations Density 0.007%

    No Known Activations