© 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. 22-GEMMASCOPE-RES-131K
    7. 66478
    Prev
    Next
    INDEX
    Explanations

    children and young people

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

    The neuron flags tokens that are numeric or include numeric/abbreviated formatting (numbers, decimals, or single‐letter initials with periods).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     девочки
    -0.96
     noirs
    -0.93
     blancs
    -0.91
    self
    -0.91
     zuen
    -0.88
    更何况
    -0.88
     cire
    -0.87
    可谓
    -0.87
     lina
    -0.87
     mercedes
    -0.86
    POSITIVE LOGITS
     children
    2.39
     kids
    1.80
     child
    1.77
     young
    1.58
     youth
    1.55
    เด็ก
    1.45
     younger
    1.34
     Children
    1.27
     kid
    1.21
    children
    1.20
    Activations Density 0.066%

    No Known Activations