© 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. 76161
    Prev
    Next
    INDEX
    Explanations

    measure of quantity or degree

    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
    ție
    -1.30
    BURGH
    -1.23
     expérimentés
    -1.13
     eerste
    -1.13
     éves
    -1.11
    NNY
    -1.11
    Perú
    -1.09
     dolayı
    -1.09
    voegen
    -1.06
    ﾛ
    -1.06
    POSITIVE LOGITS
     amount
    2.75
     number
    2.25
     level
    1.99
     likelihood
    1.98
     overall
    1.97
     ability
    1.84
     extent
    1.80
     degree
    1.75
     chances
    1.74
     already
    1.66
    Activations Density 0.148%

    No Known Activations