© 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. 33846
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
    agoza
    -0.91
    Making
    -0.90
    Sometimes
    -0.85
     sometimes
    -0.85
     Sometimes
    -0.83
    forRoot
    -0.82
    malıdır
    -0.81
    شارة
    -0.81
     Typically
    -0.79
     risolvere
    -0.79
    POSITIVE LOGITS
     тыся
    0.84
    []={
    0.84
     accepter
    0.81
     låg
    0.76
    thousands
    0.75
    lessness
    0.75
    就把
    0.74
     livet
    0.73
     подвод
    0.73
     projets
    0.73
    Activations Density 0.012%

    No Known Activations