© 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. 92158
    Prev
    Next
    INDEX
    Explanations

    skill or skills

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

    The neuron fires on programming identifiers and other capitalized tokens (e.g. names of namespaces, classes, functions, constants) in code.

    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
     グラン
    -0.80
    Payload
    -0.79
     Payload
    -0.76
    discipl
    -0.76
    UNTAIN
    -0.75
     hver
    -0.75
    ouden
    -0.75
    ूस
    -0.74
     derde
    -0.74
    روش
    -0.73
    POSITIVE LOGITS
     skill
    1.37
     skills
    1.32
     Skill
    1.09
     Skills
    1.00
     compétences
    0.99
    Skill
    0.98
    skill
    0.97
    skills
    0.90
    スキル
    0.85
     nasce
    0.85
    Activations Density 0.007%

    No Known Activations