© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84708
    Prev
    Next
    INDEX
    Explanations

    chloroform, Gurgaon, Compton, chameleon, Scully

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

    This neuron responds to longer, specialized nouns—especially chemical names (e.g. “chloroform”) and distinctive proper names or place names.

    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
     have
    -2.91
    i
    -2.89
    u
    -2.61
    (
    -2.52
    ين
    -2.44
    of
    -2.42
     was
    -2.33
    ſelves
    -2.25
    𝐍
    -2.17
    </strong>
    -2.14
    POSITIVE LOGITS
     iſt
    3.06
    蟥
    2.95
    抬手
    2.88
    沨
    2.80
    夘
    2.78
    臜
    2.73
    毟
    2.73
    渽
    2.72
    
    2.70
    ୌ
    2.69
    Activations Density 0.014%

    No Known Activations