© 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. 93705
    Prev
    Next
    INDEX
    Explanations

    max, default, length, count, byte limits

    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
    NonQuery
    -0.93
     more
    -0.84
     already
    -0.83
    Grö
    -0.82
     вже
    -0.82
    newPassword
    -0.79
     gesuchten
    -0.78
    onnaise
    -0.78
     acciaio
    -0.78
    شوند
    -0.77
    POSITIVE LOGITS
    Max
    1.21
     max
    1.10
    Default
    1.08
     Default
    1.06
     Max
    1.05
    默认
    0.99
    MAX
    0.98
    max
    0.96
     default
    0.96
    DEFAULT
    0.95
    Activations Density 0.023%

    No Known Activations