© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 93324
    Prev
    Next
    INDEX
    Explanations

    dates and events

    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
    люми
    -1.08
     cabelo
    -1.07
     voetballer
    -1.06
     ludzie
    -1.05
    yní
    -1.05
    そも
    -1.02
    これからの
    -1.02
     sprawy
    -1.00
    ├──
    -1.00
     svært
    -0.99
    POSITIVE LOGITS
     episode
    1.48
     edition
    1.34
     appearance
    1.34
     appointment
    1.29
     decision
    1.27
     iteration
    1.25
     presentation
    1.24
     application
    1.23
     announcement
    1.23
     meeting
    1.18
    Activations Density 0.030%

    No Known Activations