© 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. 34-GEMMASCOPE-RES-131K
    7. 90675
    Prev
    Next
    INDEX
    Explanations

    identifying specific nouns followed by related descriptors

    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_34/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
     three
    -1.56
     two
    -1.47
     those
    -1.38
     before
    -1.36
     some
    -1.34
     one
    -1.31
     five
    -1.30
     burgeoning
    -1.28
     six
    -1.27
     seven
    -1.27
    POSITIVE LOGITS
     unn
    1.34
    rethe
    1.23
     ผ
    1.20
    really
    1.19
    びっくり
    1.18
    mainly
    1.17
    comme
    1.16
     คา
    1.16
    possibly
    1.16
     !!!!
    1.16
    Activations Density 0.045%

    No Known Activations