© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68589
    Prev
    Next
    INDEX
    Explanations

    Planck, filesystem, enshrined

    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
    Negative Logits
     vectorstock
    -3.23
    硨
    -2.86
    齮
    -2.83
    黉
    -2.72
    眎
    -2.69
    殽
    -2.69
    踯
    -2.66
    埽
    -2.66
    棡
    -2.64
    鵙
    -2.59
    POSITIVE LOGITS
        
    3.31
    s
    2.89
    不高
    2.77
    谞
    2.55
    は
    2.55
    :
    2.52
     dizzy
    2.39
     maar
    2.36
    愎
    2.34
    —
    2.33
    Activations Density 0.006%

    No Known Activations