© 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. 44374
    Prev
    Next
    INDEX
    Explanations

    acquiring something

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

    The neuron fires on occurrences of the verb “acquire” (and its inflected forms) in text.

    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
    2
    -3.27
    c
    -3.22
    8
    -3.06
    “
    -3.06
    6
    -3.02
    time
    -2.97
    os
    -2.88
    </h1>
    -2.83
    1
    -2.81
    0
    -2.78
    POSITIVE LOGITS
    ญี่ป
    3.42
    􀂃
    3.17
     biela
    2.98
    聃
    2.92
     hebben
    2.88
     houden
    2.84
    Donativos
    2.81
    𐌽
    2.81
    ाउनलोड
    2.78
     ,‬
    2.78
    Activations Density 0.009%

    No Known Activations