© 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. 79738
    Prev
    Next
    INDEX
    Explanations

    XML and JSON structures

    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
     not
    -1.45
     by
    -1.40
     all
    -1.38
     despite
    -1.37
     from
    -1.35
     it
    -1.31
     their
    -1.31
     undeniably
    -1.28
     (
    -1.26
     had
    -1.24
    POSITIVE LOGITS
     luscious
    1.36
     famed
    1.32
    gives
    1.30
     alcune
    1.30
    *;
    1.29
     allerlei
    1.28
     betreffende
    1.27
     geleg
    1.26
     horrid
    1.23
    atization
    1.20
    Activations Density 0.005%

    No Known Activations