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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8634
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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_34/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
    -0.90
     or
    -0.86
     which
    -0.85
     либо
    -0.84
     dilengkapi
    -0.81
     Khart
    -0.81
     zwierząt
    -0.80
     because
    -0.79
     Sofía
    -0.79
     Mlle
    -0.79
    POSITIVE LOGITS
    ઃ
    0.85
     speciation
    0.84
    кова
    0.82
     mores
    0.81
     dianteiro
    0.81
    IEL
    0.80
     afirmó
    0.78
    araf
    0.78
    )$/,
    0.77
     wept
    0.77
    Activations Density 0.006%

    No Known Activations