© 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. 22-GEMMASCOPE-RES-131K
    7. 40263
    Prev
    Next
    INDEX
    Explanations

    live music and concerts

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

    The neuron fires strongly on mentions of live musical entertainment—words like “music,” “live,” “band,” “concert,” “entertainment,” and related terms signaling a musical performance.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    X
    -1.27
    P
    -1.25
    K
    -1.24
    F
    -1.16
    H
    -1.15
    G
    -1.14
    Y
    -1.13
    1
    -1.12
    x
    -1.11
    R
    -1.09
    POSITIVE LOGITS
    อร่อย
    1.28
     gorro
    1.27
    Tja
    1.22
    棪
    1.20
    сить
    1.20
    経歴
    1.20
    emerald
    1.19
     vanaf
    1.17
    pixabay
    1.16
    archivi
    1.14
    Activations Density 0.013%

    No Known Activations