© 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. 34611
    Prev
    Next
    INDEX
    Explanations

    state of the state/union

    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
    Iframe
    -0.71
    diameter
    -0.71
     Romans
    -0.69
    failure
    -0.69
    ail
    -0.69
     Failure
    -0.68
    Fails
    -0.68
     Covent
    -0.68
    堡
    -0.66
    notif
    -0.66
    POSITIVE LOGITS
     продукты
    0.71
     beeinf
    0.67
    گانی
    0.67
     VAC
    0.66
    普
    0.65
     изу
    0.65
     holo
    0.65
    Victor
    0.63
    diente
    0.62
    cili
    0.62
    Activations Density 0.057%

    No Known Activations