© 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. 70245
    Prev
    Next
    INDEX
    Explanations

    error messages and code

    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
     eikä
    -0.86
    manuelle
    -0.84
    Dlg
    -0.84
     Suomessa
    -0.81
     të
    -0.80
    Vtbl
    -0.78
     Pharma
    -0.78
    TokenNameL
    -0.77
    orgi
    -0.77
    jama
    -0.77
    POSITIVE LOGITS
    TypeError
    0.90
    builtins
    0.79
    ſt
    0.79
    WHY
    0.75
     Antioch
    0.75
    はん
    0.75
    kih
    0.74
     Miyazaki
    0.72
    MainThread
    0.72
    ~\
    0.71
    Activations Density 0.045%

    No Known Activations