© 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. 116120
    Prev
    Next
    INDEX
    Explanations

    song featuring artist

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

    The neuron preferentially fires on list‐formatting tokens—especially numerals and punctuation marks like commas, parentheses, and dashes used in track listings.

    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
    有一定的
    -0.86
    strcpy
    -0.81
     llegue
    -0.81
     Bloomfield
    -0.75
     Säure
    -0.75
    icker
    -0.73
    omencl
    -0.72
     نسبت
    -0.71
    Johns
    -0.71
    ühle
    -0.70
    POSITIVE LOGITS
     featuring
    4.56
     ft
    4.16
     feat
    3.97
    feat
    3.73
     Featuring
    3.56
     Ft
    3.31
    Featuring
    3.28
    featuring
    3.19
    Feat
    3.16
    ft
    3.05
    Activations Density 0.039%

    No Known Activations