© 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. 41882
    Prev
    Next
    INDEX
    Explanations

    ignite, ignition, spark

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

    The neuron is triggered by occurrences of the root “ignit-,” i.e. words like ignite, ignites, ignition, ignited, 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
    er
    -4.09
    m
    -3.28
    of
    -2.95
    C
    -2.94
    S
    -2.80
    ve
    -2.78
    ar
    -2.77
    en
    -2.75
    fe
    -2.73
    our
    -2.61
    POSITIVE LOGITS
    Médaille
    2.42
     apartamentos
    2.38
    punkten
    2.30
    ]
    2.30
    蒾
    2.28
    潆
    2.23
     expandir
    2.23
     usamos
    2.20
    ﺢ
    2.20
     如果
    2.19
    Activations Density 0.004%

    No Known Activations