© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 97965
    Prev
    Next
    INDEX
    Explanations

    cover artwork

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

    The main thing this neuron does is detect mentions of “cover art” (or closely related terms like “cover artwork”).

    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
    icer
    -0.88
    vestream
    -0.85
    urando
    -0.82
     docu
    -0.79
    فیلم
    -0.79
    örü
    -0.79
    Documentary
    -0.78
     マンガ
    -0.77
    lalom
    -0.77
     string
    -0.76
    POSITIVE LOGITS
     cover
    2.83
     artwork
    2.56
    cover
    1.98
    Cover
    1.92
     covers
    1.88
     Cover
    1.82
     portada
    1.81
    artwork
    1.78
     art
    1.73
    封面
    1.66
    Activations Density 0.052%

    No Known Activations