© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118877
    Prev
    Next
    INDEX
    Explanations

    spatial zones and distances

    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
    γων
    -0.94
    effectively
    -0.82
    numsp
    -0.80
     Honours
    -0.79
    支付宝
    -0.78
    sedur
    -0.77
    Endereço
    -0.77
    neder
    -0.77
    λυ
    -0.77
    HTTPS
    -0.77
    POSITIVE LOGITS
     zones
    1.55
     zone
    1.54
     buffer
    1.33
     mapped
    1.30
     buffers
    1.27
     areas
    1.23
     protection
    1.19
     setback
    1.17
     setbacks
    1.15
     maps
    1.13
    Activations Density 0.013%

    No Known Activations