© 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. 90541
    Prev
    Next
    INDEX
    Explanations

    the necessary technical noun

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

    The neuron fires on the single most important technical action or object word that names a question’s core task.

    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
     to
    -1.25
     or
    -1.23
     (
    -1.12
     and
    -1.02
     потому
    -1.02
    ,
    -0.97
     数据
    -0.96
    textSize
    -0.95
    strokeWeight
    -0.94
    ススメ
    -0.94
    POSITIVE LOGITS
     entire
    1.85
     necessary
    1.74
     needed
    1.64
     necessario
    1.52
     feltro
    1.48
     already
    1.48
     required
    1.42
    seamnă
    1.42
     necessarie
    1.42
     felpa
    1.39
    Activations Density 0.144%

    No Known Activations