© 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. 83700
    Prev
    Next
    INDEX
    Explanations

    song writers or performers

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

    This neuron fires on numeric tokens—years, track‐time durations, catalog numbers, and similar numbers in music credit or track‐listing metadata.

    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
    romancer
    -0.79
    noz
    -0.75
    ionale
    -0.73
    angnya
    -0.73
    fillable
    -0.72
    zinha
    -0.72
     popraw
    -0.72
     derra
    -0.72
    actus
    -0.71
     dziś
    -0.71
    POSITIVE LOGITS
    جميع
    1.02
     performed
    0.94
     developed
    0.90
     additional
    0.89
     credited
    0.85
     misericordia
    0.85
     keyboards
    0.84
     except
    0.84
    を発
    0.84
     originally
    0.84
    Activations Density 0.053%

    No Known Activations