© 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. 81299
    Prev
    Next
    INDEX
    Explanations

    in the, in binary

    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
     in
    -0.93
     of
    -0.89
     on
    -0.88
     thinks
    -0.87
     according
    -0.81
     says
    -0.81
     died
    -0.80
     have
    -0.79
     gave
    -0.78
    יך
    -0.78
    POSITIVE LOGITS
     case
    1.02
    踅
    0.98
     diesem
    0.98
     우리
    0.97
    case
    0.96
     this
    0.96
    particularly
    0.96
     [\
    0.94
    Etter
    0.93
    だけではなく
    0.93
    Activations Density 0.002%

    No Known Activations