© 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. 11054
    Prev
    Next
    INDEX
    Explanations

    image filenames and numbers

    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
     in
    -1.21
     but
    -1.09
     of
    -1.05
     September
    -1.05
     there
    -1.04
    writel
    -1.04
    اعده
    -1.01
     солнца
    -1.01
    なのが
    -1.01
    ²+
    -1.00
    POSITIVE LOGITS
    zaron
    1.14
     persecu
    1.14
     juz
    1.09
    𝐉
    1.08
     indepen
    1.08
     culte
    1.07
     seigneur
    1.05
    最近は
    1.05
     strategia
    1.05
     patatas
    1.03
    Activations Density 0.011%

    No Known Activations