© 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. 98621
    Prev
    Next
    INDEX
    Explanations

    Tamar, Taman, Mar, Calam, Armin

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

    This neuron fires on capitalized proper names (including personal names and scientific/genus names) not at sentence beginnings.

    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
     أحد
    -0.73
     bahawa
    -0.71
    CountDown
    -0.71
    ovým
    -0.70
     watercolour
    -0.68
    innerHeight
    -0.68
     droite
    -0.67
    lji
    -0.66
     herbicide
    -0.64
     Merton
    -0.64
    POSITIVE LOGITS
    resort
    0.89
     nabi
    0.85
     overlying
    0.84
    ⦅
    0.82
     overlapping
    0.82
    defineProperty
    0.80
     ufe
    0.79
     neighboring
    0.77
     illimit
    0.75
     Resort
    0.74
    Activations Density 0.008%

    No Known Activations