© 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. 22-GEMMASCOPE-RES-131K
    4. 69100
    Prev
    Next
    INDEX
    Explanations

    additional quantity or amount

    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
     AsyncTask
    -1.36
     mantenga
    -1.33
     bekämp
    -1.32
    vestidos
    -1.32
     nossa
    -1.30
     ragazzo
    -1.29
     olahraga
    -1.29
    FONTE
    -1.27
     schützen
    -1.25
     produttore
    -1.25
    POSITIVE LOGITS
     $
    1.70
     
    1.35
    لهم
    1.28
     Dijo
    1.17
     Tampoco
    1.13
    can
    1.13
     maravillosa
    1.13
    es
    1.13
     Parece
    1.06
     прекрасно
    1.06
    Activations Density 0.011%

    No Known Activations