© 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. 22-GEMMASCOPE-RES-131K
    4. 385
    Prev
    Next
    INDEX
    Explanations

    availability and finding

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

    This neuron lights up on extended answer or narrative prose (longer content‐rich sentences) rather than short titles or question lines.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     сразу
    -1.23
    「
    -1.19
    mouthed
    -1.13
    -1.08
    property
    -1.03
    ru
    -1.02
     that
    -1.02
    将
    -1.01
     resultado
    -0.98
    做
    -0.98
    POSITIVE LOGITS
     availability
    1.66
     online
    1.27
     вони
    1.24
    ープル
    1.24
     available
    1.23
    перь
    1.23
    讫
    1.23
     Início
    1.22
    する方法
    1.20
     elér
    1.20
    Activations Density 0.043%

    No Known Activations