© 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. 59895
    Prev
    Next
    INDEX
    Explanations

    technical documentation or articles

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

    This neuron activates on capitalized proper names, especially personal 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
    品の
    -2.55
     a
    -2.45
    翾
    -2.39
     unsere
    -2.33
     externas
    -2.31
    慊
    -2.30
     возможность
    -2.27
    形の
    -2.27
    e
    -2.22
    鬟
    -2.22
    POSITIVE LOGITS
    y
    3.20
    絰
    3.13
    1
    2.86
    鞮
    2.78
    蹰
    2.63
    不会
    2.55
     welchem
    2.48
     jenen
    2.36
    9
    2.33
    st
    2.27
    Activations Density 0.005%

    No Known Activations