© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7164
    Prev
    Next
    INDEX
    Explanations

    analytical methods and conditions

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

    The neuron activates for the word "analytical" when it appears in scientific contexts, particularly related to research methods and techniques.

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

    The neuron specifically detects occurrences of the word “Analytical” in technical or scientific text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    鲠
    -3.50
    sandalia
    -3.08
     แต่
    -2.89
     The
    -2.83
    ꜄
    -2.70
    絎
    -2.56
     was
    -2.56
    pecabe
    -2.53
     그는
    -2.48
    ajuste
    -2.47
    POSITIVE LOGITS
    B
    3.52
    呖
    3.27
    He
    3.17
     حتى
    3.03
    ization
    3.03
    H
    3.03
    Even
    2.95
    ࿚
    2.88
    For
    2.80
    When
    2.77
    Activations Density 0.002%

    No Known Activations