© 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. 22-GEMMASCOPE-RES-131K
    4. 104458
    Prev
    Next
    INDEX
    Explanations

    between plants and the external

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

    This neuron detects relationships between objects and their properties, particularly identifying the connection between nouns and their attributes.

    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_22/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
     
    -1.20
     EVEN
    -1.06
     voyant
    -1.05
    EVEN
    -1.04
    で大
    -1.02
     пър
    -0.98
     связи
    -0.98
    甚至
    -0.98
     wondrous
    -0.97
     INITI
    -0.97
    POSITIVE LOGITS
     other
    1.27
     their
    1.20
     its
    1.16
     using
    1.15
     on
    1.13
     übrigen
    1.13
     trying
    1.11
     when
    1.11
     being
    1.09
     Those
    1.06
    Activations Density 0.147%

    No Known Activations