© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 404
    Prev
    Next
    INDEX
    Explanations

    programming keywords

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

    This neuron detects Doctrine ORM annotation syntax, i.e. the `@ORM\...` annotations with parentheses (like ManyToOne, JoinColumn, Column) in PHP 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
    Már
    -0.84
    ánt
    -0.77
     ਅਤੇ
    -0.76
    博多
    -0.76
     conocido
    -0.72
     に関する
    -0.71
    czegó
    -0.69
     seeming
    -0.69
    Initially
    -0.68
     Extended
    -0.68
    POSITIVE LOGITS
    isburg
    0.76
     fairness
    0.75
    нев
    0.74
     nullable
    0.74
     hautes
    0.73
    rada
    0.73
     Fairness
    0.73
    ਭ
    0.73
    気軽に
    0.72
    Tall
    0.72
    Activations Density 0.005%

    No Known Activations