© 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. 34-GEMMASCOPE-RES-131K
    7. 33620
    Prev
    Next
    INDEX
    Explanations

    Sales / Edit " Assign

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

    This neuron fires strongly on domain-specific technical terms and jargon (especially Salesforce/Apex identifiers and error 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_34/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
     account
    -0.96
    隣の
    -0.89
     customer
    -0.81
    ctg
    -0.79
    nolia
    -0.79
    鋰
    -0.77
     něk
    -0.76
    meida
    -0.76
    junct
    -0.75
    ctt
    -0.75
    POSITIVE LOGITS
    userModel
    0.81
    assignment
    0.80
    Assignment
    0.75
     ASSIGN
    0.74
     小
    0.73
    Assign
    0.72
    imagePath
    0.72
    咽
    0.71
    acha
    0.71
     Gris
    0.71
    Activations Density 0.022%

    No Known Activations