© 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. 81734
    Prev
    Next
    INDEX
    Explanations

    type followed by colon

    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
    ctable
    -1.14
    şim
    -1.09
    Gdy
    -1.05
    今月
    -1.01
    Já
    -0.97
    CodeAttribute
    -0.96
    AxisSize
    -0.96
    Извест
    -0.92
    readonly
    -0.91
     WASTE
    -0.91
    POSITIVE LOGITS
     acreditar
    0.86
     esimerkiksi
    0.86
    でて
    0.84
     miền
    0.81
    olkata
    0.81
     päivä
    0.80
    enser
    0.79
    ium
    0.78
     vieler
    0.77
     fremden
    0.76
    Activations Density 0.004%

    No Known Activations