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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20968
    Prev
    Next
    INDEX
    Explanations

    the act of gaining something

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

    The neuron activates on various forms of the root word “acquire,” i.e., words related to acquisition (acquire, acquires, acquired, acquisition).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    𓋼
    -2.17
    which
    -1.95
    鹛
    -1.91
    “
    -1.87
    or
    -1.84
    
    -1.79
    -
    -1.77
    time
    -1.77
    ):
    -1.76
     assorted
    -1.71
    POSITIVE LOGITS
    ㌧
    2.22
    他
    1.94
    􀂃
    1.91
     somber
    1.85
    ungkinkan
    1.83
    
    1.80
     okno
    1.77
    
    1.73
     ostro
    1.73
     hebben
    1.68
    Activations Density 0.028%

    No Known Activations