© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 85154
    Prev
    Next
    INDEX
    Explanations

    grants and programs

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

    The neuron strongly activates on verbs that describe grant‐ or funding‐supported actions (e.g. train, address, bolster, prepare, implement).

    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
    なくなって
    -1.20
    Sejarah
    -1.20
     rafra
    -1.19
     véhic
    -1.14
     catég
    -1.12
    姈
    -1.12
    Kdo
    -1.10
     virtuelle
    -1.09
    優惠
    -1.09
     visuel
    -1.09
    POSITIVE LOGITS
     in
    1.57
     with
    1.47
     his
    1.44
     from
    1.41
     by
    1.39
     for
    1.38
     "
    1.34
     “
    1.34
     and
    1.23
     už
    1.20
    Activations Density 0.114%

    No Known Activations