© 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. 22-GEMMASCOPE-RES-131K
    7. 75114
    Prev
    Next
    INDEX
    Explanations

    boast, showcase

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

    This neuron activates on occurrences of the verb “boast” (and its forms), marking statements that tout or highlight features.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    the verb "boast" or "boasts" when describing features, qualities, or attributes that something possesses or offers.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    verbs that signal promotional boasting or prominently highlighting features, qualities, or achievements.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     and
    -2.41
    戰爭
    -1.89
     besluit
    -1.80
     toneladas
    -1.77
    戬
    -1.75
     которы
    -1.74
    瓒
    -1.72
    嘥
    -1.71
    ്ട
    -1.70
     That
    -1.70
    POSITIVE LOGITS
     of
    2.53
    '
    2.23
     enam
    2.23
    x
    2.05
    …
    2.00
     soooo
    1.98
    {
    1.97
    是最
    1.95
     …..
    1.95
     sooo
    1.94
    Activations Density 0.019%

    No Known Activations