© 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. 65327
    Prev
    Next
    INDEX
    Explanations

    romantic

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

    The neuron detects list‐style punctuation and conjunctions (parentheses, commas, “or,” etc.) marking enumerated items.

    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
     neceffary
    -0.83
    circuit
    -0.74
    ȅ
    -0.73
     Azevedo
    -0.69
    ング
    -0.68
     aluminum
    -0.68
    きた
    -0.68
     Flexible
    -0.67
     preco
    -0.67
    arkov
    -0.67
    POSITIVE LOGITS
     romantic
    5.16
    romantic
    4.16
     роман
    3.63
     roman
    3.58
     Romantic
    3.56
    Romantic
    3.53
     romance
    3.14
    roman
    2.42
     román
    2.27
    romance
    2.27
    Activations Density 0.049%

    No Known Activations