© 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. 119993
    Prev
    Next
    INDEX
    Explanations

    plans to, has dug, off to

    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
    ,
    -2.08
     I
    -1.88
     we
    -1.63
     in
    -1.53
     this
    -1.48
    อื่น
    -1.40
     and
    -1.30
    /*++
    -1.22
    zation
    -1.19
     other
    -1.18
    POSITIVE LOGITS
     ihres
    1.58
     zrobić
    1.52
     nochmals
    1.51
     budete
    1.42
    没什么
    1.41
     будут
    1.35
    ilerini
    1.34
    ㅑ
    1.30
     seçenek
    1.30
     herself
    1.26
    Activations Density 0.021%

    No Known Activations