© 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. 22-GEMMASCOPE-RES-131K
    7. 130363
    Prev
    Next
    INDEX
    Explanations

    originating from various sources

    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
     or
    -1.24
     did
    -0.98
     each
    -0.96
    ztes
    -0.95
     Sab
    -0.93
    mapp
    -0.93
    IdList
    -0.93
    ´
    -0.90
    Schemes
    -0.90
     schen
    -0.89
    POSITIVE LOGITS
     existing
    1.55
     materials
    1.31
    existing
    1.24
     leftover
    1.22
     sélectionner
    1.21
     vorhand
    1.19
     scegliere
    1.15
     verur
    1.15
     dikeluarkan
    1.14
     available
    1.13
    Activations Density 0.102%

    No Known Activations