© 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. 7361
    Prev
    Next
    INDEX
    Explanations

    brand names and technical terms

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

    The neuron mainly picks out named entities—proper nouns, brand or product names, and function/model names.

    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
    <
    -2.95
    er
    -2.67
     They
    -2.44
     \
    -2.38
    "
    -2.28
    它们
    -2.20
     anstatt
    -2.20
    to
    -2.20
    is
    -2.19
     impresionante
    -2.17
    POSITIVE LOGITS
     間取り
    2.31
    注意事
    2.23
     …)
    2.19
     弁当
    2.14
    ]
    2.13
    椟
    2.13
     個室
    2.08
    …).
    2.03
    I
    2.02
    …”
    2.00
    Activations Density 0.019%

    No Known Activations