© 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. 981
    Prev
    Next
    INDEX
    Explanations

    Scotch, 3M, Peloton, Q:

    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
     Lump
    -0.82
    FUN
    -0.78
     quels
    -0.73
    îné
    -0.72
    blowing
    -0.71
     Manson
    -0.71
    ข่าว
    -0.70
    loyment
    -0.70
    unusual
    -0.70
    面对
    -0.69
    POSITIVE LOGITS
     Scotch
    1.88
    Scot
    1.23
     scotch
    1.10
     SCOT
    1.02
    scot
    1.02
     Scot
    1.01
     Avery
    0.92
    cotch
    0.91
     Minnesota
    0.89
     tape
    0.83
    Activations Density 0.029%

    No Known Activations