© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109077
    Prev
    Next
    INDEX
    Explanations

    music releases and songs

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

    The neuron strongly activates on numeric tokens (e.g. years, track timings, counts, and other digit sequences).

    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
    cey
    -1.13
     bloemen
    -1.05
     變
    -1.02
    變成
    -1.01
    取决
    -0.99
    改變
    -0.94
     Poet
    -0.93
    obacz
    -0.93
    觀眾
    -0.93
     帳
    -0.91
    POSITIVE LOGITS
     listen
    1.73
     listeners
    1.56
    Listen
    1.51
     listening
    1.49
     Listen
    1.47
    listen
    1.37
     listened
    1.29
     opener
    1.27
     listener
    1.23
     Listening
    1.23
    Activations Density 0.052%

    No Known Activations