© 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. 11780
    Prev
    Next
    INDEX
    Explanations

    stadium presence

    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
     wahre
    -2.63
     THEY
    -2.59
     według
    -2.44
    栳
    -2.39
    $.
    -2.34
     identifiés
    -2.34
     Können
    -2.34
     européens
    -2.33
     Erkenntnisse
    -2.33
    还不是
    -2.31
    POSITIVE LOGITS
     группу
    2.55
    奩
    2.50
    s
    2.41
     previsto
    2.36
     operation
    2.36
     nimmer
    2.34
    ”;
    2.33
    })
    2.30
     blau
    2.27
     gelb
    2.25
    Activations Density 0.005%

    No Known Activations