© 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. 38220
    Prev
    Next
    INDEX
    Explanations

    GUI components and programming constructs

    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
    correlated
    -0.75
    Loyalty
    -0.74
    RTEE
    -0.73
     كما
    -0.73
    Viri
    -0.72
    sschutz
    -0.71
    chanan
    -0.71
    брав
    -0.69
     burrows
    -0.69
    heon
    -0.69
    POSITIVE LOGITS
     Checkbox
    1.05
    Checkbox
    0.96
     AudioClip
    0.96
    Choice
    0.91
    peer
    0.89
     TextField
    0.88
    Label
    0.86
    Scrollbar
    0.82
    East
    0.81
    Peer
    0.80
    Activations Density 0.019%

    No Known Activations