© 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. 1144
    Prev
    Next
    INDEX
    Explanations

    easy to clean

    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
     it
    -1.98
     then
    -1.91
     consideradas
    -1.86
     sabias
    -1.74
     decoradas
    -1.73
     kunnen
    -1.71
     aisladas
    -1.65
     conocidas
    -1.64
    以上です
    -1.63
     marcadas
    -1.54
    POSITIVE LOGITS
     and
    2.13
     yaris
    1.46
     XXXII
    1.35
     yd
    1.31
    ~~~~~
    1.30
     of
    1.30
     meski
    1.27
     londres
    1.25
     بسیاری
    1.24
     borealis
    1.22
    Activations Density 0.025%

    No Known Activations