© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 41067
    Prev
    Next
    INDEX
    Explanations

    conferring resistance

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

    The neuron detects the verb "confer" followed by a description of properties or qualities being granted to something.

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

    This neuron activates on occurrences of the verb “confer” (in forms like confer, confers, conferring).

    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
    柃
    -2.39
    衕
    -2.38
    OTHERS
    -2.38
    鯪
    -2.09
    "});
    -2.06
    ᅚ
    -2.05
    ſam
    -2.03
    ᠂
    -1.96
    </h1>
    -1.92
    */}
    -1.91
    POSITIVE LOGITS
     
    2.11
    </sup>
    2.06
    Since
    2.03
    谖
    1.97
    *
    1.91
    There
    1.88
    medriver
    1.86
     "
    1.83
    你可以
    1.83
    事实上
    1.80
    Activations Density 0.013%

    No Known Activations