© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40141
    Prev
    Next
    INDEX
    Explanations

    nostalgia for past eras and items

    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
    魮
    -3.00
    谖
    -2.72
     termed
    -2.59
    哢
    -2.55
    👒
    -2.39
     prossima
    -2.34
    涠
    -2.33
    ｐ
    -2.27
     praised
    -2.27
    髣
    -2.23
    POSITIVE LOGITS
    ’
    3.17
    ↵
    3.06
    {
    2.88
    '
    2.75
     
    2.72
     “
    2.70
    $
    2.25
    e
    2.20
    并不
    2.16
     {
    2.14
    Activations Density 0.005%

    No Known Activations