© 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. 34-GEMMASCOPE-RES-131K
    4. 84875
    Prev
    Next
    INDEX
    Explanations

    open house, open bar

    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
     OPENING
    -0.77
     držav
    -0.76
     teaspoons
    -0.76
     springtime
    -0.75
    opening
    -0.75
    gule
    -0.72
    phorbia
    -0.72
    routines
    -0.71
     zakresie
    -0.71
    名は
    -0.70
    POSITIVE LOGITS
     enrollment
    1.01
     concept
    0.95
    concept
    0.89
    Concept
    0.85
     open
    0.83
    enrollment
    0.82
     Concept
    0.81
     invitation
    0.81
     availability
    0.80
     air
    0.76
    Activations Density 0.032%

    No Known Activations