© 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. 82575
    Prev
    Next
    INDEX
    Explanations

    gn, Gn, Gnu, Gna, GnF, GnT, GnS

    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
     essentially
    -0.81
     Ell
    -0.77
    achable
    -0.75
     unintended
    -0.75
     advent
    -0.72
     Efficient
    -0.72
    窓
    -0.72
     побо
    -0.72
     efficiently
    -0.71
    pples
    -0.71
    POSITIVE LOGITS
     Gn
    1.02
     gn
    0.89
    Gn
    0.84
     GN
    0.81
     Mins
    0.81
    bustion
    0.79
    ⓒ
    0.77
    nima
    0.72
     blocker
    0.71
     Histories
    0.71
    Activations Density 0.040%

    No Known Activations