© 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. 45381
    Prev
    Next
    INDEX
    Explanations

    music reviews and interviews

    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
     harmonics
    -0.78
     didn
    -0.75
     footage
    -0.71
    fieldId
    -0.71
     jonka
    -0.71
    Clips
    -0.70
     imaginations
    -0.68
     Geo
    -0.67
    Imagin
    -0.67
     Clips
    -0.66
    POSITIVE LOGITS
     music
    1.26
    music
    1.16
    Music
    1.10
    review
    1.09
     review
    1.04
     recenz
    1.04
     musikk
    1.02
     reviewer
    1.01
    MUSIC
    1.01
    Interview
    1.00
    Activations Density 0.049%

    No Known Activations