© 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. 34-GEMMASCOPE-RES-131K
    7. 7311
    Prev
    Next
    INDEX
    Explanations

    Kaz names and places

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

    The neuron activates on occurrences of the three‐letter sequence “kaz” (or its close variant “caz”) appearing anywhere in words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Ге
    -0.79
    BindView
    -0.71
    loginPage
    -0.71
    iov
    -0.70
    恐れ
    -0.69
    Led
    -0.69
    tapkan
    -0.69
     Omb
    -0.68
    Bayes
    -0.68
    Bindings
    -0.68
    POSITIVE LOGITS
    maier
    0.91
    terms
    0.87
    pread
    0.77
     IERC
    0.77
    kazu
    0.77
    ften
    0.77
    ковка
    0.75
    seers
    0.75
     Kaz
    0.74
    рма
    0.73
    Activations Density 0.023%

    No Known Activations