© 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. 36064
    Prev
    Next
    INDEX
    Explanations

    counting numbers and names

    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
     kült
    -0.88
    zaamheid
    -0.85
     Paramètres
    -0.84
     dapur
    -0.82
    März
    -0.82
    🗝
    -0.82
     americanos
    -0.81
     -¿
    -0.81
    だと思います
    -0.80
    formato
    -0.80
    POSITIVE LOGITS
    ־ה
    0.84
    itale
    0.82
    ങ്ങള
    0.82
    ᄐ
    0.80
     Laver
    0.80
     регуляр
    0.80
     …
    0.80
    ladelphia
    0.79
    дне
    0.77
    合物
    0.77
    Activations Density 0.196%

    No Known Activations