© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107698
    Prev
    Next
    INDEX
    Explanations

    competitive grants

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

    This neuron detects mentions of monetary figures and funding/grant amounts.

    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
    urare
    -0.77
     Hardin
    -0.68
    Overrides
    -0.68
     kerusakan
    -0.68
     difficulties
    -0.68
    zany
    -0.68
    맷
    -0.68
     scherm
    -0.67
     maven
    -0.67
    ónde
    -0.67
    POSITIVE LOGITS
     grant
    1.22
    gran
    1.17
    Competitive
    1.13
     grantee
    1.13
     competitive
    1.08
    grant
    1.08
     grants
    1.07
     gran
    1.07
    competition
    0.98
     Grant
    0.97
    Activations Density 0.041%

    No Known Activations