© 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. 22-GEMMASCOPE-RES-131K
    4. 39890
    Prev
    Next
    INDEX
    Explanations

    competing descriptions

    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_22/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
    okai
    -0.89
    blins
    -0.88
     téléphonique
    -0.88
     sonde
    -0.82
     мысль
    -0.82
    ereka
    -0.81
    sometimes
    -0.79
    FileList
    -0.78
     occidentale
    -0.78
    Especially
    -0.78
    POSITIVE LOGITS
     clash
    1.23
     competing
    1.18
     contest
    1.16
     battle
    1.16
     ambos
    1.15
     showdown
    1.15
     quarrel
    1.14
     dispute
    1.13
     both
    1.13
     contesting
    1.13
    Activations Density 0.133%

    No Known Activations