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. 34-GEMMASCOPE-RES-131K
    4. 7792
    Prev
    Next
    INDEX
    Explanations

    Blo, Testimonials, Open

    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
     Arkansas
    -0.84
     Winf
    -0.78
     Römer
    -0.77
     SGS
    -0.76
    Lexington
    -0.75
    zension
    -0.73
     Minecraft
    -0.71
    mitsubishi
    -0.71
    Montag
    -0.71
     гиб
    -0.70
    POSITIVE LOGITS
     plotly
    1.27
    plotly
    1.09
     Nair
    0.83
     Ronaldo
    0.82
    🍱
    0.81
    xref
    0.80
    getLayout
    0.80
    ネン
    0.78
     Kraken
    0.78
    mapbox
    0.77
    Activations Density 0.013%

    No Known Activations