© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127200
    Prev
    Next
    INDEX
    Explanations

    transfer of data or actions

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

    The neuron activates specifically on occurrences of the word “transfer” (in any case).

    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
    s
    -2.84
    P
    -2.83
    '
    -2.77
    8
    -2.67
    H
    -2.55
    AT
    -2.47
    </h1>
    -2.36
    n
    -2.34
    \
    -2.31
    などで
    -2.30
    POSITIVE LOGITS
    </em>
    3.02
    锜
    3.00
    इटम
    2.72
     and
    2.69
    unicaciones
    2.64
    ],
    2.61
    ”.
    2.59
    谖
    2.58
    摇了
    2.53
    .’
    2.52
    Activations Density 0.014%

    No Known Activations