© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 31349
    Prev
    Next
    INDEX
    Explanations

    childhood health and development outcomes

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

    The neuron activates strongly for the word "childhood" and related concepts about early life development.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on occurrences of the word “Childhood,” especially in titles or headings.

    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
    처
    -0.87
     ниже
    -0.86
    の位置
    -0.85
     hombros
    -0.80
    ventilated
    -0.79
    カーテン
    -0.78
     مساء
    -0.77
    premiere
    -0.77
    の上に
    -0.77
    綺麗に
    -0.77
    POSITIVE LOGITS
     memories
    1.77
     trauma
    1.27
     spent
    1.16
     friend
    1.13
     nostalgia
    1.12
     summers
    1.10
     memory
    1.09
     recollections
    1.09
     homes
    1.04
     obesity
    1.04
    Activations Density 0.026%

    No Known Activations