© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 59049
    Prev
    Next
    INDEX
    Explanations

    Led Zeppelin, LED terms, ledger

    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
     sided
    -0.87
     ला
    -0.82
     unt
    -0.81
     Repe
    -0.78
     person
    -0.77
     place
    -0.77
     .
    -0.75
     uncertain
    -0.73
     divide
    -0.73
     highest
    -0.70
    POSITIVE LOGITS
     Zeppelin
    1.48
     astray
    1.34
    gers
    1.15
    gend
    0.99
    Zep
    0.97
    oux
    0.96
    ership
    0.95
     Led
    0.91
     Zep
    0.90
    GERS
    0.90
    Activations Density 0.017%

    No Known Activations