© 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. 34-GEMMASCOPE-RES-131K
    4. 73457
    Prev
    Next
    INDEX
    Explanations

    grow into or out of

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

    The neuron detects forms of the word "grow" and related concepts of development or expansion.

    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
     находя
    -1.04
    carrying
    -1.02
     carrying
    -0.97
     giu
    -0.96
     améli
    -0.95
    鹛
    -0.95
     bulle
    -0.94
     CARRY
    -0.94
     galax
    -0.92
     jenner
    -0.92
    POSITIVE LOGITS
     into
    1.43
     crops
    1.10
     accustomed
    1.05
     in
    1.03
     from
    1.01
     out
    0.99
     pains
    0.98
     weary
    0.98
     by
    0.98
     impatient
    0.96
    Activations Density 0.024%

    No Known Activations