© 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. 66265
    Prev
    Next
    INDEX
    Explanations

    total percentage ratio average

    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
    measurement
    -1.14
     siè
    -1.11
     Quantification
    -1.10
    Measurement
    -1.09
    statistic
    -1.08
     níveis
    -1.07
     illustre
    -1.05
     inond
    -1.03
    denken
    -1.02
     célè
    -1.01
    POSITIVE LOGITS
     difference
    1.43
     time
    1.27
     percent
    1.26
     ratio
    1.25
     average
    1.23
     change
    1.23
     percentage
    1.22
     trend
    1.18
     absolute
    1.17
     total
    1.13
    Activations Density 0.071%

    No Known Activations