© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22524
    Prev
    Next
    INDEX
    Explanations

    symbionts and ions

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

    The neuron detects biological and technical terminology containing "ion" syllables, particularly in scientific names and technical terms.

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

    The neuron responds to the character sequence “ion” (i-o-n) within words.

    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
    as
    -3.02
    while
    -2.98
     riservata
    -2.83
    ？）
    -2.64
    from
    -2.63
     bluse
    -2.61
     یا
    -2.56
    where
    -2.56
     auxquelles
    -2.53
    there
    -2.50
    POSITIVE LOGITS
    {
    3.00
     '
    2.70
     insanlar
    2.14
     erfolgreiche
    2.14
     be
    2.13
    }
    2.09
     französische
    2.05
     原因
    2.05
     正面
    2.03
    piecze
    2.02
    Activations Density 0.012%

    No Known Activations