© 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. 110856
    Prev
    Next
    INDEX
    Explanations

    Billboard Hot chart

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

    The neuron activates on numeric tokens, in particular on numbers denoting chart positions or other statistics.

    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
     альбом
    -0.84
     álbum
    -0.84
     album
    -0.81
    asaran
    -0.78
     альбо
    -0.77
     功效
    -0.77
     violon
    -0.75
     Rugg
    -0.75
     Definitions
    -0.75
    𝓮
    -0.73
    POSITIVE LOGITS
     Hot
    1.16
    Hot
    1.02
     US
    0.91
    Bil
    0.82
    US
    0.80
     HOT
    0.80
    חות
    0.77
     sencillos
    0.74
    bill
    0.74
     hot
    0.74
    Activations Density 0.028%

    No Known Activations