© 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. 34-GEMMASCOPE-RES-131K
    4. 109479
    Prev
    Next
    INDEX
    Explanations

    confirming data availability

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

    This neuron spots formal disclosure or declaration statements (e.g. conflict-of-interest and data-availability declarations) in academic text.

    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
     dikeluarkan
    -0.85
    akir
    -0.83
     его
    -0.83
     também
    -0.83
     Rabatt
    -0.82
     kedua
    -0.82
     adquis
    -0.81
     también
    -0.79
     Puedes
    -0.79
     Cómo
    -0.77
    POSITIVE LOGITS
     declare
    1.71
    Declare
    1.52
     Declare
    1.35
     declares
    1.24
    declare
    1.20
     disclose
    1.19
     declared
    1.18
     declaration
    1.09
     competing
    1.08
     declara
    1.08
    Activations Density 0.011%

    No Known Activations