© 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. 57553
    Prev
    Next
    INDEX
    Explanations

    postcard or postcode

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

    The neuron specifically detects occurrences of the word “postcard” (and its plural form).

    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
    呖
    -2.44
     необходимые
    -2.25
     тво
    -2.17
    ⚋
    -2.11
    犰
    -2.08
     It
    -2.05
     свою
    -2.02
    </em>
    -2.02
    h
    -1.99
    ⮜
    -1.98
    POSITIVE LOGITS
    '
    3.02
    './
    2.20
     '
    2.13
    ни
    2.13
     Our
    2.09
     Entdecken
    2.05
     That
    2.03
     postcards
    1.91
     the
    1.85
     rupture
    1.84
    Activations Density 0.003%

    No Known Activations