© 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. 10-GEMMASCOPE-RES-131K
    7. 119484
    Prev
    Next
    INDEX
    Explanations

    artists, directors, albums, and bands

    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_10/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
    ennessee
    -1.29
    urlar
    -1.18
    schedulers
    -1.16
    ল
    -1.13
    pirate
    -1.13
    龵
    -1.12
    
    -1.12
     parola
    -1.09
    About
    -1.09
     phosphate
    -1.08
    POSITIVE LOGITS
    uble
    1.40
    的关键
    1.33
     both
    1.22
    明確
    1.20
    Quer
    1.20
     now
    1.20
    。『
    1.19
    ᅟ
    1.18
     éxitos
    1.17
    我们需要
    1.17
    Activations Density 0.167%

    No Known Activations