© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81512
    Prev
    Next
    INDEX
    Explanations

    donating and fundraising

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

    The neuron is responding to very high–frequency/common function words (i.e. tokens like “the,” “to,” “is,” “and,” pronouns, etc.) rather than any particular content 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
    migrationBuilder
    -1.11
     Confidence
    -1.08
    Confidence
    -0.99
    confidence
    -0.97
    waits
    -0.96
    मे
    -0.93
    welcome
    -0.91
    मा
    -0.91
    ğından
    -0.91
    upgrade
    -0.88
    POSITIVE LOGITS
     donate
    1.48
     donating
    1.44
     donation
    1.36
     donations
    1.33
     generosity
    1.20
     donated
    1.17
     fundraising
    1.16
    捐
    1.07
    抜粋
    1.07
    Donation
    1.05
    Activations Density 0.050%

    No Known Activations