© 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. 130768
    Prev
    Next
    INDEX
    Explanations

    with other entities

    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
    -1.93
     when
    -1.74
     it
    -1.71
     this
    -1.65
     that
    -1.55
     during
    -1.54
     can
    -1.45
     which
    -1.45
     after
    -1.43
     During
    -1.43
    POSITIVE LOGITS
     other
    2.08
     various
    2.06
     여러
    2.00
     several
    1.99
    several
    1.88
    various
    1.85
    ต่างๆ
    1.84
     várias
    1.71
    other
    1.69
     vários
    1.68
    Activations Density 0.065%

    No Known Activations