© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109668
    Prev
    Next
    INDEX
    Explanations

    section marker

    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
     Expertise
    -0.86
     Matsu
    -0.83
    Expertise
    -0.82
     головой
    -0.82
     merak
    -0.81
    tilor
    -0.81
    devtool
    -0.79
     vart
    -0.79
    _",
    -0.78
    }{*}{}
    -0.77
    POSITIVE LOGITS
    occupe
    0.85
     postaci
    0.84
     figuras
    0.83
     दोनों
    0.80
    There
    0.79
     öfter
    0.79
     lemah
    0.78
    While
    0.77
    UNA
    0.76
    ومت
    0.74
    Activations Density 0.001%

    No Known Activations