© 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. 10-GEMMASCOPE-RES-131K
    7. 74844
    Prev
    Next
    INDEX
    Explanations

    work, productivity, space, concentration, office

    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_10/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
     rigide
    -1.36
     autonome
    -1.29
    abbix
    -1.26
    Bahnhof
    -1.23
     pongo
    -1.17
     veren
    -1.16
    ironically
    -1.15
    Habe
    -1.14
     sonore
    -1.10
    Beweg
    -1.09
    POSITIVE LOGITS
     your
    1.20
     vollständige
    1.16
     only
    1.13
     tylko
    1.13
     
    1.12
     this
    1.11
     or
    1.09
     =
    1.09
    قاد
    1.09
     Zwecke
    1.08
    Activations Density 0.048%

    No Known Activations