© 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. 65811
    Prev
    Next
    INDEX
    Explanations

    Social Links, Atlus games

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

    The neuron fires on named entities—especially character names, game titles, and other proper nouns.

    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
    "
    -1.47
     again
    -1.45
    us
    -1.32
    2
    -1.29
     beruht
    -1.27
     &
    -1.24
    ,,,
    -1.23
    those
    -1.22
    v
    -1.21
    ，「
    -1.20
    POSITIVE LOGITS
    っちり
    1.41
    を書
    1.40
     annat
    1.37
     träd
    1.36
     щоб
    1.35
     PML
    1.34
    Banyak
    1.30
    鏖
    1.27
     stately
    1.27
    ͑
    1.27
    Activations Density 0.010%

    No Known Activations