© 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. 34-GEMMASCOPE-RES-131K
    7. 90012
    Prev
    Next
    INDEX
    Explanations

    examples starting with specific tokens

    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
     both
    -0.88
    lové
    -0.83
     considerable
    -0.81
     gradually
    -0.81
    Jawab
    -0.80
     reducing
    -0.79
    limmer
    -0.77
    ắc
    -0.77
    āli
    -0.76
    Resident
    -0.75
    POSITIVE LOGITS
    ut
    0.90
     toutefois
    0.89
     advertiser
    0.84
     podrían
    0.83
     nowy
    0.83
     sponsorship
    0.82
    ratis
    0.82
     podría
    0.82
     mone
    0.81
     vieles
    0.81
    Activations Density 0.001%

    No Known Activations