© 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. 81314
    Prev
    Next
    INDEX
    Explanations

    mapreduce

    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
    irov
    -0.75
     Endowment
    -0.72
    idade
    -0.71
    辯
    -0.71
     countryside
    -0.69
     подъ
    -0.68
    umen
    -0.68
    Dis
    -0.67
     إل
    -0.67
    ISING
    -0.66
    POSITIVE LOGITS
     reducer
    1.43
    Reduce
    1.16
     Reduce
    1.16
     reducers
    1.15
    reduce
    1.14
    reducers
    1.14
     Reducer
    1.13
     combin
    1.10
     reduce
    1.09
     combining
    1.05
    Activations Density 0.034%

    No Known Activations