© 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. 34-GEMMASCOPE-RES-131K
    7. 107762
    Prev
    Next
    INDEX
    Explanations

    surprise or confusion

    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_34/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
    ключения
    -0.85
    น่า
    -0.85
    ccn
    -0.85
    namb
    -0.82
    isamment
    -0.81
    žiai
    -0.81
    VolleyError
    -0.81
    APPY
    -0.79
    ㄉ
    -0.78
    の可能性
    -0.77
    POSITIVE LOGITS
     Huh
    2.66
    Huh
    2.41
     huh
    2.38
     WTF
    2.25
     WHAT
    2.25
    huh
    2.05
    WHAT
    1.91
     Wha
    1.84
    WTF
    1.80
    wtf
    1.70
    Activations Density 0.058%

    No Known Activations