© 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. 22-GEMMASCOPE-RES-131K
    7. 36537
    Prev
    Next
    INDEX
    Explanations

    or Precedential/Non-Precedential classification

    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
     kasa
    -1.27
     devin
    -1.19
     banane
    -1.17
     publier
    -1.16
    ")),
    -1.16
     corriger
    -1.15
     taba
    -1.15
    𝕿
    -1.12
     vinyle
    -1.12
    ダーク
    -1.12
    POSITIVE LOGITS
     if
    1.88
     or
    1.80
     each
    1.44
     that
    1.30
     either
    1.30
     when
    1.27
     it
    1.24
     If
    1.20
     for
    1.20
     part
    1.18
    Activations Density 0.006%

    No Known Activations