© 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. 34-GEMMASCOPE-RES-131K
    4. 115886
    Prev
    Next
    INDEX
    Explanations

    government assessment and work schemes

    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
    actividades
    -0.78
    dotti
    -0.78
    mujeres
    -0.76
    Programming
    -0.76
     graças
    -0.73
     thảm
    -0.73
    queued
    -0.72
     Jugendlichen
    -0.72
    רְ
    -0.68
    htub
    -0.68
    POSITIVE LOGITS
     scheme
    4.75
     schemes
    3.88
    scheme
    3.52
     Scheme
    3.22
    Scheme
    3.17
     SCHEME
    2.88
     Schemes
    2.80
    schemes
    2.78
    Schemes
    2.61
    SCHEME
    2.59
    Activations Density 0.030%

    No Known Activations