© 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. 19333
    Prev
    Next
    INDEX
    Explanations

    Clarence and DV names

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

    The neuron activates on single-word named entities—proper names and acronyms or initialisms.

    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
    0
    -3.72
    <i>
    -3.38
    \
    -3.31
    </b>
    -3.13
    the
    -2.97
     is
    -2.95
    .
    -2.77
    <
    -2.61
    ’
    -2.58
     or
    -2.42
    POSITIVE LOGITS
    ꪔ
    2.88
    謌
    2.77
     CALIFOR
    2.77
    桄
    2.72
    ၟ
    2.64
     erhi
    2.63
    zembro
    2.58
    ଢ
    2.52
     adulta
    2.50
    iffance
    2.50
    Activations Density 0.066%

    No Known Activations