© 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. 66027
    Prev
    Next
    INDEX
    Explanations

    programming identifiers

    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
     unele
    -1.12
     folosi
    -0.96
    chufe
    -0.95
     кілька
    -0.93
     oamenii
    -0.92
     aufgestellt
    -0.89
     ajutor
    -0.88
    慢慢的
    -0.88
     două
    -0.87
    anging
    -0.86
    POSITIVE LOGITS
    _
    1.77
    _{
    1.20
     for
    1.08
    _{\
    1.08
     because
    1.02
     strconv
    0.94
     ushort
    0.94
     ilç
    0.93
     venezol
    0.92
    пя
    0.91
    Activations Density 0.143%

    No Known Activations