© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 208
    Prev
    Next
    INDEX
    Explanations

    C/C++ code structure

    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_22/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
     havia
    -0.85
    oli
    -0.84
    z
    -0.84
    を
    -0.82
    ista
    -0.82
    branded
    -0.81
     نک
    -0.81
    sum
    -0.81
    u
    -0.80
    ests
    -0.80
    POSITIVE LOGITS
    héro
    1.03
    alimentos
    0.96
     that
    0.95
     deliciosos
    0.94
    nhung
    0.94
    ामी
    0.93
    tranh
    0.92
    să
    0.92
    ısında
    0.92
     serce
    0.91
    Activations Density 0.004%

    No Known Activations