© 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. 22-GEMMASCOPE-RES-131K
    7. 68054
    Prev
    Next
    INDEX
    Explanations

    announcements and commitments

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

    The neuron specializes in spotting the promotional lead sentences of corporate press releases announcing new services or offerings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ׇ
    -1.81
     ویتامین
    -1.70
    อร่อย
    -1.67
     朝食
    -1.53
     витами
    -1.50
     gritos
    -1.48
     katholischen
    -1.46
     meravigli
    -1.45
    ἴ
    -1.45
    Produktion
    -1.43
    POSITIVE LOGITS
    וּ
    1.76
    靭
    1.46
     Pingback
    1.41
     раст
    1.41
    怦
    1.38
     bicarbon
    1.38
     لاعب
    1.38
    рѣ
    1.36
    修炼
    1.35
     customers
    1.34
    Activations Density 0.117%

    No Known Activations