© 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. 77757
    Prev
    Next
    INDEX
    Explanations

    research grant applications

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

    The neuron is detecting grant and resource identifiers (NIH/CRISP grant numbers, resource codes, and similar funding‐related alphanumeric sequences).

    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
     raison
    -0.94
    toward
    -0.78
    jaci
    -0.75
    ⌄
    -0.74
    bnf
    -0.73
     ICollection
    -0.71
    halla
    -0.71
    años
    -0.71
     Banken
    -0.71
     UNIVERS
    -0.70
    POSITIVE LOGITS
     GM
    0.83
     grant
    0.81
     rainha
    0.75
     grants
    0.72
    paran
    0.71
    lared
    0.71
     지원
    0.71
     الحق
    0.68
     unterscheiden
    0.68
    Modificar
    0.68
    Activations Density 0.089%

    No Known Activations