© 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. 130718
    Prev
    Next
    INDEX
    Explanations

    personal narratives and activism

    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
     if
    -1.57
     they
    -1.30
     still
    -1.21
    eniem
    -1.18
    either
    -1.18
     are
    -1.12
     usually
    -1.12
     individuals
    -1.10
     geluid
    -1.09
     either
    -1.08
    POSITIVE LOGITS
     ใช้
    1.38
     สาม
    1.23
     herself
    1.20
     autora
    1.10
    后来
    1.10
    ㄨ
    1.09
     crochê
    1.08
    ཊ
    1.08
     Irán
    1.06
    ชีวิต
    1.05
    Activations Density 0.071%

    No Known Activations