© 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. 9192
    Prev
    Next
    INDEX
    Explanations

    java package names

    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
    namientos
    -1.70
    :^{
    -1.67
     Truppen
    -1.62
     their
    -1.58
     its
    -1.53
    onymes
    -1.48
     szybko
    -1.47
     pulseira
    -1.46
     your
    -1.46
     uhr
    -1.45
    POSITIVE LOGITS
    1
    2.22
    2
    2.19
    9
    2.05
    5
    1.89
    0
    1.77
     is
    1.66
    7
    1.63
     are
    1.63
    3
    1.61
    >
    1.61
    Activations Density 0.008%

    No Known Activations