© 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. 37946
    Prev
    Next
    INDEX
    Explanations

    evolution and evolutionary ideas

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

    discussions of evolutionary processes in scientific literature.

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

    The neuron detects references to evolutionary conservation or timescales of evolution.

    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
    mités
    -0.89
    🔥🔥🔥
    -0.84
    یکا
    -0.83
    ácia
    -0.81
    :@
    -0.79
     BECK
    -0.79
     galima
    -0.78
     financials
    -0.77
    پا
    -0.77
    »).
    -0.76
    POSITIVE LOGITS
     evolution
    5.34
     evolutionary
    5.00
    evolution
    4.66
     Evolution
    4.34
    Evolution
    4.31
     evolved
    4.13
     Evolutionary
    3.81
     EVOLUTION
    3.55
     evolu
    3.44
     evolución
    3.44
    Activations Density 0.225%

    No Known Activations