© 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. 98353
    Prev
    Next
    INDEX
    Explanations

    layers or substrates

    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
    arella
    -0.92
    𝙶
    -0.84
    éfono
    -0.83
    urcht
    -0.83
    áře
    -0.82
     Secrétaire
    -0.81
    tenberg
    -0.81
    ждународ
    -0.81
    towych
    -0.81
     overhanging
    -0.80
    POSITIVE LOGITS
     layer
    2.09
     outer
    1.69
     layers
    1.67
     inner
    1.56
     Layer
    1.45
    Layer
    1.34
     outermost
    1.33
     backing
    1.30
    layer
    1.27
    outer
    1.25
    Activations Density 0.153%

    No Known Activations