© 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. 10-GEMMASCOPE-RES-131K
    7. 102445
    Prev
    Next
    INDEX
    Explanations

    working to create

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

    The neuron strongly activates on verbs that denote proactive efforts or initiatives (e.g. make, develop, provide, help, try).

    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
     or
    -2.41
     for
    -2.27
     on
    -2.16
    懺
    -1.67
     Makes
    -1.65
     most
    -1.61
     five
    -1.61
    錚
    -1.60
     from
    -1.56
     eight
    -1.56
    POSITIVE LOGITS
     alfabe
    1.45
     ander
    1.45
     voient
    1.41
     itali
    1.40
     Kontrol
    1.40
    ♪♪
    1.38
    叼
    1.36
    rays
    1.35
     hırka
    1.34
     injust
    1.33
    Activations Density 0.037%

    No Known Activations