© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49785
    Prev
    Next
    INDEX
    Explanations

    AT-series

    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
    ponym
    -0.78
     Chris
    -0.70
     scare
    -0.69
     it
    -0.69
    onite
    -0.68
     gwaran
    -0.68
     connected
    -0.68
     aktar
    -0.66
     fragt
    -0.66
     inocente
    -0.66
    POSITIVE LOGITS
     series
    1.58
     Series
    1.45
    SERIES
    1.39
    Series
    1.30
     série
    1.27
    series
    1.23
     SERIES
    1.20
     séries
    1.20
     serie
    1.19
     серии
    1.18
    Activations Density 0.051%

    No Known Activations