© 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. 127747
    Prev
    Next
    INDEX
    Explanations

    taming, domestication, untamed

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

    The neuron activates on occurrences of the root “tame,” detecting words like tame, taming, and untamed.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    language about taming or domestication—turning something wild or unruly into something controlled or domesticated.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the word "tame" and its variants (taming, tamed, untamed) in various contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered 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
    '
    -3.80
    </h3>
    -2.31
     '
    -2.11
    al
    -2.05
    身后的
    -1.99
    ?'
    -1.98
    』（
    -1.92
    犼
    -1.84
    锨
    -1.80
    🔴
    -1.77
    POSITIVE LOGITS
    AN
    2.56
     trochę
    2.16
    AT
    2.16
    沨
    2.14
     bedeckt
    2.13
    These
    2.09
     ваш
    2.06
    他の
    2.06
    A
    2.05
    婞
    2.00
    Activations Density 0.007%

    No Known Activations