© 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. 9655
    Prev
    Next
    INDEX
    Explanations

    innovative products and devices

    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
     ۲
    -1.39
    ureusement
    -1.33
    recently
    -1.19
     основные
    -1.19
    rierung
    -1.16
     تحص
    -1.16
    Its
    -1.14
    wanna
    -1.13
    IFICACIÓN
    -1.13
     fréquemment
    -1.12
    POSITIVE LOGITS
     new
    2.47
     innovative
    1.73
     ideas
    1.60
     that
    1.51
     innovation
    1.51
     what
    1.47
     novel
    1.46
     products
    1.46
     first
    1.45
     product
    1.44
    Activations Density 0.042%

    No Known Activations