© 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. 60000
    Prev
    Next
    INDEX
    Explanations

    sensing and detection

    np_acts-logits-general · gemini-2.5-flash-lite

    technical documentation and programming-related content.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    IOT
    -0.85
    Inflater
    -0.82
    ↵
    -0.80
    cest
    -0.78
     ostat
    -0.78
    灵气
    -0.78
    чия
    -0.77
    颌
    -0.77
     remplacement
    -0.77
     آیفون
    -0.77
    POSITIVE LOGITS
     sensing
    1.40
     senses
    1.26
     perception
    1.20
     sensed
    1.16
     induction
    1.09
     Sensing
    1.08
     consciousness
    1.06
     scanning
    1.02
     detection
    0.98
     mental
    0.96
    Activations Density 0.004%

    No Known Activations