Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 334
    Prev
    Next
    INDEX
    Explanations

    public code keywords

    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
     it
    -1.91
    ಱ
    -1.62
     there
    -1.61
     Conseils
    -1.54
     Portail
    -1.50
    hogany
    -1.46
    '~
    -1.45
     regulador
    -1.45
     helicóptero
    -1.42
     Hauteur
    -1.41
    POSITIVE LOGITS
     зараз
    1.52
    聍
    1.51
     for
    1.47
    AL
    1.47
    حياتها
    1.45
     of
    1.43
     will
    1.39
    getMock
    1.34
    hộp
    1.34
     börja
    1.32
    Activations Density 0.001%

    No Known Activations