© 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. 10-GEMMASCOPE-RES-131K
    7. 112018
    Prev
    Next
    INDEX
    Explanations

    future research development

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

    The neuron strongly activates on words referring to the planning, design, or development of something.

    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
     большинстве
    -1.52
     таком
    -1.48
     wtedy
    -1.46
     desconocido
    -1.45
     reservado
    -1.42
     разница
    -1.36
     dispuesto
    -1.35
    ář
    -1.34
     valiente
    -1.34
     donné
    -1.31
    POSITIVE LOGITS
     on
    1.54
     based
    1.52
     with
    1.51
     regarding
    1.46
     by
    1.45
     and
    1.45
     today
    1.43
     which
    1.39
     both
    1.39
    =“
    1.36
    Activations Density 0.055%

    No Known Activations