© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49694
    Prev
    Next
    INDEX
    Explanations

    purchase acquires

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

    The neuron flags salient content tokens—especially proper names (organizations, places, publication titles) and other high-information words (adverbs, modals, key verbs) rather than common function words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     sold
    -0.88
     donating
    -0.87
     sale
    -0.85
     entreg
    -0.84
     supplying
    -0.83
    tonsoft
    -0.83
     delivered
    -0.83
     retornar
    -0.82
     delivering
    -0.81
     leave
    -0.81
    POSITIVE LOGITS
     acquires
    1.41
     acquire
    1.40
     took
    1.36
     inherit
    1.33
     übernahm
    1.30
     acquiring
    1.29
     acquired
    1.26
     takeover
    1.23
    acquire
    1.22
     inher
    1.20
    Activations Density 0.055%

    No Known Activations