© 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. 49619
    Prev
    Next
    INDEX
    Explanations

    song choruses and refrains

    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
    knapp
    -0.88
    Cinco
    -0.82
    ocellular
    -0.82
    푼
    -0.77
    هذا
    -0.75
     CCA
    -0.75
     formales
    -0.74
    cionar
    -0.73
    kund
    -0.73
     Calvert
    -0.73
    POSITIVE LOGITS
     chorus
    4.47
     Chorus
    3.16
    Chorus
    3.14
    chorus
    3.13
     refrain
    2.59
    CHORUS
    2.47
     CHORUS
    2.36
     hook
    2.16
     chor
    2.14
    サビ
    1.96
    Activations Density 0.035%

    No Known Activations