© 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. 107421
    Prev
    Next
    INDEX
    Explanations

    expressing range or variation

    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
     including
    -0.85
    𝓽
    -0.81
     things
    -0.80
    四大
    -0.76
    nä
    -0.76
    五大
    -0.75
     almost
    -0.73
     incluir
    -0.73
    包括
    -0.73
     it
    -0.72
    POSITIVE LOGITS
     ranging
    6.22
    ranging
    5.28
     ranged
    4.94
     range
    4.44
     ranges
    4.16
    range
    3.78
    Range
    3.36
    ranges
    3.36
     Ranges
    3.22
     Range
    3.14
    Activations Density 0.340%

    No Known Activations