© 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. 13576
    Prev
    Next
    INDEX
    Explanations

    adding to existing collections

    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
     deux
    -1.05
     dennoch
    -0.99
    dags
    -0.97
     kuiten
    -0.94
    rillation
    -0.93
    gione
    -0.93
     zweifel
    -0.92
     BOTH
    -0.92
     späteren
    -0.92
     though
    -0.91
    POSITIVE LOGITS
     already
    2.53
     уже
    2.08
    already
    1.91
    Already
    1.77
     existing
    1.74
     bereits
    1.73
     вже
    1.66
     Already
    1.62
     allerede
    1.59
     già
    1.58
    Activations Density 0.047%

    No Known Activations