© 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. 33488
    Prev
    Next
    INDEX
    Explanations

    song chart success

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

    The neuron is keyed to detect named titles—especially album or song names rendered as proper‐noun phrases.

    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
    頜
    -0.96
    "\\
    -0.94
     ہیں
    -0.94
    époque
    -0.92
     môžu
    -0.91
     vedno
    -0.90
    gaben
    -0.90
     mengatakan
    -0.87
     comenzado
    -0.87
     vannak
    -0.87
    POSITIVE LOGITS
     received
    2.13
     receive
    1.52
     was
    1.46
     sold
    1.29
     Received
    1.26
    Received
    1.23
     became
    1.19
     won
    1.14
     sell
    1.13
     become
    1.10
    Activations Density 0.079%

    No Known Activations