© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 73778
    Prev
    Next
    INDEX
    Explanations

    dates, version numbers, code comments

    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_22/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
     різних
    -1.41
     bedeut
    -1.39
     vielfäl
    -1.36
     hilfre
    -1.34
     different
    -1.33
     anspruchs
    -1.30
     dubbio
    -1.30
     geeigne
    -1.27
     口コミ
    -1.26
     sorgfäl
    -1.25
    POSITIVE LOGITS
    吅
    1.25
    了你
    1.23
     invokingState
    1.21
     celle
    1.19
     вече
    1.15
     kort
    1.15
    ࿆
    1.15
     cik
    1.14
     mondta
    1.14
     ville
    1.13
    Activations Density 0.071%

    No Known Activations