© 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. 22-GEMMASCOPE-RES-131K
    7. 39706
    Prev
    Next
    INDEX
    Explanations

    what i am watching

    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
    😡
    -1.27
    AfterViewInit
    -1.23
     It
    -1.20
     السياس
    -1.16
    🤮
    -1.16
     технологі
    -1.13
     our
    -1.13
    {}/
    -1.12
     behöver
    -1.11
    ViewChild
    -1.08
    POSITIVE LOGITS
    おわりに
    1.23
     やすい
    1.15
    loze
    1.15
    もうすぐ
    1.14
    Glej
    1.14
    私は
    1.12
    最近は
    1.10
     Breath
    1.07
    梅雨
    1.07
    czego
    1.05
    Activations Density 0.009%

    No Known Activations