© 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. 71377
    Prev
    Next
    INDEX
    Explanations

    Edwin names, asi beginnings

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

    The neuron activates on tokens that begin with an uppercase letter—i.e. proper nouns and class/type 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
    鈊
    -2.58
    ,”
    -2.53
    》（
    -2.36
    亮点
    -2.13
    入った
    -2.08
    除此
    -2.06
     east
    -2.05
    ."
    -2.05
     ecstatic
    -2.05
    Other
    -2.03
    POSITIVE LOGITS
    
    2.73
    킁
    2.67
    咴
    2.56
    ᷆
    2.47
    这
    2.42
     представителей
    2.39
    埽
    2.34
    ໌
    2.31
     merav
    2.25
     parlato
    2.25
    Activations Density 0.001%

    No Known Activations