© 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. 59245
    Prev
    Next
    INDEX
    Explanations

    music production and recording

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

    The neuron responds to temporal progress language—verbs and expressions that describe when and how work (e.g. albums or projects) began, continued, or was carried out over time.

    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
    Ẓ
    -1.09
    inio
    -0.84
     subscribed
    -0.83
     rotor
    -0.81
    クタイ
    -0.81
    imetsu
    -0.79
    жка
    -0.78
    bumptech
    -0.77
    衞
    -0.76
     Walter
    -0.75
    POSITIVE LOGITS
     recording
    2.17
     writing
    1.84
     recorded
    1.81
     songwriting
    1.63
    recording
    1.56
    Recording
    1.55
     studio
    1.49
    studio
    1.48
    writing
    1.45
    制作
    1.45
    Activations Density 0.044%

    No Known Activations