© 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. 38307
    Prev
    Next
    INDEX
    Explanations

    definition/classification

    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
    𝖙
    -0.89
     inmig
    -0.81
    Namara
    -0.80
    phological
    -0.77
     tradicional
    -0.77
     drastic
    -0.77
     extravagant
    -0.76
     qualitative
    -0.76
     .=
    -0.75
     Verwaltung
    -0.74
    POSITIVE LOGITS
    NATURE
    1.29
     NATURE
    1.10
    natur
    1.05
    Nature
    1.05
    nature
    1.03
    iliger
    0.95
     tof
    0.95
    тельностью
    0.94
    ❐
    0.91
     Nature
    0.90
    Activations Density 0.050%

    No Known Activations