Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8702
    Prev
    Next
    INDEX
    Explanations

    entering and exiting locations

    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
     ďal
    -0.83
    orso
    -0.82
     apartament
    -0.82
    ')}}"
    -0.81
    sima
    -0.81
     slutet
    -0.79
    ("/{
    -0.78
     ними
    -0.77
     दुनिया
    -0.77
     in
    -0.76
    POSITIVE LOGITS
     features
    1.91
     entering
    1.82
    Entering
    1.73
     Entering
    1.63
     entered
    1.44
     Features
    1.40
    Features
    1.38
     enter
    1.38
     entrance
    1.33
     interior
    1.30
    Activations Density 0.026%

    No Known Activations