© 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. 65309
    Prev
    Next
    INDEX
    Explanations

    praises excellence

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

    The neuron fires on emphatically positive descriptive words (especially “brilliant” and other strong praise adjectives).

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

    strongly positive evaluative adjectives that express praise or enthusiasm.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the word "brilliant" used in positive contexts or reviews.

    oai_token-act-pair · claude-4-5-sonnetTriggered 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
     bailarina
    -1.72
    ﹍
    -1.66
    恸
    -1.57
    完成です
    -1.55
    
    -1.53
    哔
    -1.51
    ﯽ
    -1.46
    第一章
    -1.45
    了啊
    -1.45
    檢查
    -1.44
    POSITIVE LOGITS
    のは
    1.84
     –
    1.63
    ти
    1.53
     vorigen
    1.53
     [
    1.48
    );
    1.48
    <h3>
    1.46
    <b>
    1.45
     yaitu
    1.45
    </h5>
    1.42
    Activations Density 0.022%

    No Known Activations