© 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. 1135
    Prev
    Next
    INDEX
    Explanations

    physical gestures or movements

    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
     were
    -2.70
    しますが
    -2.61
     There
    -2.59
     Those
    -2.44
    after
    -2.44
     secretive
    -2.39
     Surprisingly
    -2.38
     While
    -2.36
     Going
    -2.33
    There
    -2.31
    POSITIVE LOGITS
    {
    2.72
     vijf
    2.69
    .")
    2.63
     nimmer
    2.47
    骝
    2.45
    "
    2.42
    2.25
     possono
    2.22
    ʻ
    2.20
    ."
    2.16
    Activations Density 0.001%

    No Known Activations