© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 40320
    Prev
    Next
    INDEX
    Explanations

    bad things happening

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

    This neuron fires on vague placeholder nouns like “thing,” “things,” or “something” used generically in 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_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
    不同
    -1.23
    異なる
    -1.13
     hvor
    -1.06
    crème
    -1.05
    ようです
    -1.05
     Меня
    -1.02
    tainty
    -1.02
    ленный
    -1.01
     Represents
    -1.01
    ようで
    -1.00
    POSITIVE LOGITS
     happening
    1.70
     happen
    1.52
     happens
    1.41
     happened
    1.35
     about
    1.29
     in
    1.23
    但这
    1.06
    见状
    1.05
    happ
    1.05
    窯
    1.03
    Activations Density 0.060%

    No Known Activations