© 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. 120158
    Prev
    Next
    INDEX
    Explanations

    Hookah, water, ki

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

    The neuron fires on any token containing the letter sequence “ki.”

    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
    讴
    -2.41
     of
    -2.34
    嚆
    -2.33
    ちゃう
    -2.31
    謦
    -2.30
    I
    -2.20
     Unterneh
    -2.16
     the
    -2.16
    ㉕
    -2.13
    …,
    -2.05
    POSITIVE LOGITS
     atendido
    2.47
    '
    2.47
    ⸫
    2.34
    嚒
    2.33
     semelhantes
    2.19
    絰
    2.17
     confirmado
    2.14
    ௡
    2.13
    grafik
    2.09
     umožňuje
    2.09
    Activations Density 0.000%

    No Known Activations