© 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. 33022
    Prev
    Next
    INDEX
    Explanations

    field, evaluation, current, 2

    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
     của
    -1.33
     of
    -1.05
    various
    -0.99
     which
    -0.92
    うち
    -0.87
     которые
    -0.86
     other
    -0.86
     также
    -0.84
     này
    -0.83
    atürk
    -0.83
    POSITIVE LOGITS
    出了一
    0.90
     jedenfalls
    0.90
    telefone
    0.87
     Cuckoo
    0.86
    HOUT
    0.86
    volent
    0.86
    mogat
    0.84
     chuck
    0.81
    (":");
    0.79
    ILabel
    0.78
    Activations Density 0.001%

    No Known Activations