© 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. 34744
    Prev
    Next
    INDEX
    Explanations

    musical notes and songs

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    sự
    -0.83
     móg
    -0.74
    thiết
    -0.71
    ogno
    -0.71
    звичай
    -0.70
    jok
    -0.70
     polecam
    -0.69
     fianco
    -0.68
    습니다
    -0.68
     đen
    -0.68
    POSITIVE LOGITS
     tune
    2.27
     symphony
    2.03
     harmony
    1.91
     melody
    1.79
     tunes
    1.73
    tune
    1.72
    harmon
    1.63
     song
    1.60
     harmonic
    1.55
     tuning
    1.52
    Activations Density 0.033%

    No Known Activations