© 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. 3590
    Prev
    Next
    INDEX
    Explanations

    received word or report

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

    The neuron flags tokens that signal reported information—words indicating “receipt” or “reporting” of news or data (e.g. received, word, news, information, sources).

    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
    kwür
    -1.45
    skon
    -1.45
    ysa
    -1.45
     humeur
    -1.39
    哙
    -1.38
    躂
    -1.34
    denk
    -1.34
    linawan
    -1.31
    閙
    -1.31
    kozá
    -1.30
    POSITIVE LOGITS
     that
    2.02
     from
    1.84
     rằng
    1.41
    =
    1.38
     lentejuelas
    1.34
    cembre
    1.30
     sämtliche
    1.27
    <
    1.26
    antium
    1.25
    どうなる
    1.24
    Activations Density 0.044%

    No Known Activations