© 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. 10-GEMMASCOPE-RES-131K
    7. 90857
    Prev
    Next
    INDEX
    Explanations

    how something is

    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_10/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
    硨
    -2.16
    Their
    -1.88
    噲
    -1.77
    夤
    -1.76
    等は
    -1.76
    Ố
    -1.74
    They
    -1.71
    琑
    -1.71
    ᯾
    -1.68
     Igreja
    -1.67
    POSITIVE LOGITS
    <bos>
    2.31
    .
    1.77
    ”
    1.71
     {
    1.68
     erstes
    1.61
    ;
    1.61
     varies
    1.55
    s
    1.55
    )
    1.52
     diverse
    1.51
    Activations Density 0.028%

    No Known Activations