© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 42613
    Prev
    Next
    INDEX
    Explanations

    Proper nouns

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

    The neuron is detecting proper-name entities—personal names, place names, organization names, etc.

    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
    퐼
    -2.38
    峩
    -2.23
     importants
    -2.22
     remarquable
    -2.22
    Of
    -2.19
    唻
    -2.14
     スペシャル
    -2.13
    ㉗
    -2.13
     usati
    -2.06
    錞
    -2.05
    POSITIVE LOGITS
    ↵
    3.05
    </em>
    2.91
     "
    2.77
    ם
    2.56
     These
    2.56
     Hinblick
    2.45
     vorigen
    2.44
    -"
    2.42
     Previously
    2.38
     There
    2.36
    Activations Density 0.081%

    No Known Activations