© 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. 34602
    Prev
    Next
    INDEX
    Explanations

    eligible, registered, qualified

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

    The neuron fires on phrasing that specifies who something is provided or sent “to” or “for,” i.e. marking distribution or access targets.

    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
     diferentes
    -0.97
     الأخرى
    -0.94
     הארץ
    -0.91
    ITAN
    -0.90
     möglich
    -0.88
    buyer
    -0.87
    (""),
    -0.84
     createState
    -0.82
    耘
    -0.81
     possible
    -0.81
    POSITIVE LOGITS
     registered
    2.91
     eligible
    2.30
    registered
    2.05
     enrolled
    1.98
     Registered
    1.85
     qualifying
    1.80
    Registered
    1.77
     qualified
    1.77
     anyone
    1.77
     members
    1.73
    Activations Density 0.111%

    No Known Activations