© 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. 22-GEMMASCOPE-RES-131K
    4. 9585
    Prev
    Next
    INDEX
    Explanations

    natural processes and phenomena

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

    phrases that reference natural biological processes or structures as models or inspiration.

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

    The neuron strongly activates on mentions of “natural” or “nature”–related terms (e.g. natural photosynthesis, natural materials, Nature).

    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
    ̳
    -1.04
    otene
    -0.98
    secta
    -0.94
    กร
    -0.94
    eamiento
    -0.93
    
    -0.92
    澄
    -0.91
    chter
    -0.91
    着一个
    -0.91
     gardien
    -0.90
    POSITIVE LOGITS
     naturally
    2.13
     natural
    1.85
    natural
    1.64
     φυσ
    1.49
    naturally
    1.49
    Naturally
    1.38
     Naturally
    1.34
    Natural
    1.33
     NATURAL
    1.29
     есте
    1.27
    Activations Density 0.200%

    No Known Activations