© 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. 64650
    Prev
    Next
    INDEX
    Explanations

    grant funding

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

    The neuron fires on mentions of grants, funding awards, or related financial‐award language (e.g. “receives,” “awarded,” dollar amounts, “grant,” etc.).

    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
    therly
    -0.81
    翃
    -0.78
     trase
    -0.78
     removals
    -0.78
    ྂ
    -0.77
     JOY
    -0.77
     PRIV
    -0.76
    uristic
    -0.75
     recru
    -0.75
     cresc
    -0.74
    POSITIVE LOGITS
     grant
    5.41
     grants
    4.66
    grant
    3.70
     funding
    3.61
     Grants
    3.27
     Grant
    3.23
    grants
    3.19
    Grant
    3.03
    Grants
    2.91
     funds
    2.78
    Activations Density 0.069%

    No Known Activations