© 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. 20456
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by words

    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
     -
    -3.41
     einige
    -2.98
    –
    -2.91
    というわけで
    -2.89
    o
    -2.75
     {
    -2.72
     What
    -2.58
    了她
    -2.56
     algunos
    -2.47
    了我
    -2.45
    POSITIVE LOGITS
    "
    4.13
    ,’
    3.42
    .’
    3.36
    蹰
    3.33
    踽
    3.16
    🫱
    3.09
    ’.
    2.94
    ,”
    2.86
    螓
    2.80
    vantaged
    2.73
    Activations Density 0.004%

    No Known Activations