© 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. 71519
    Prev
    Next
    INDEX
    Explanations

    function calls and code syntax

    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
     "
    -1.40
     to
    -1.25
     
    -1.23
     was
    -1.21
     for
    -1.21
    for
    -1.15
     \"
    -1.10
     courseId
    -1.09
     usando
    -1.09
     blir
    -1.03
    POSITIVE LOGITS
    ஒ
    1.34
     your
    1.29
     our
    1.27
     EVERY
    1.24
    ஏ
    1.23
    嵜
    1.23
     every
    1.21
    Fär
    1.20
    Kenapa
    1.19
     almend
    1.18
    Activations Density 0.002%

    No Known Activations