© 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. 22-GEMMASCOPE-RES-131K
    7. 54429
    Prev
    Next
    INDEX
    Explanations

    past actions or states

    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
    thodox
    -0.81
    “:
    -0.80
    hesis
    -0.79
    !\!\
    -0.79
     gunung
    -0.78
    є
    -0.76
    更是
    -0.76
    ificantly
    -0.76
    inghouse
    -0.76
    cellent
    -0.75
    POSITIVE LOGITS
     previous
    1.80
     previously
    1.66
     предыду
    1.52
    previously
    1.41
    previous
    1.41
    Previously
    1.36
     already
    1.23
    Previous
    1.23
     sebelumnya
    1.21
    Already
    1.20
    Activations Density 0.050%

    No Known Activations