© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66277
    Prev
    Next
    INDEX
    Explanations

    Ex, Male, process, administrative abbreviations

    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
    {
    -1.53
    :
    -1.45
    </sup>
    -1.30
    *{
    -1.17
    Therefore
    -1.15
    Though
    -1.13
    Those
    -1.13
    They
    -1.10
     "
    -1.09
     be
    -1.08
    POSITIVE LOGITS
    rebbe
    1.27
    衣裙
    1.21
     calitate
    1.19
     piele
    1.13
     ragaz
    1.10
    ಞ
    1.09
     Ucraina
    1.09
     venit
    1.09
     reale
    1.09
    ddar
    1.09
    Activations Density 0.022%

    No Known Activations