© 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. 98357
    Prev
    Next
    INDEX
    Explanations

    Index or entry point

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

    The neuron fires on action‐oriented verbs and keywords (like “can,” “trigger,” “reload,” “refresh,” “update,” etc.) that describe steps or commands in code or instructions.

    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
     chré
    -1.16
     Những
    -1.02
     韩
    -0.98
     блюдо
    -0.95
    Suara
    -0.91
    Memories
    -0.91
     Nếu
    -0.90
    κει
    -0.90
     sikre
    -0.88
     Ngoài
    -0.88
    POSITIVE LOGITS
     all
    1.09
     every
    0.86
     momenti
    0.84
    ˨
    0.84
    𝐱
    0.82
     by
    0.81
     updated
    0.80
     general
    0.80
     most
    0.79
    All
    0.78
    Activations Density 0.002%

    No Known Activations