© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65178
    Prev
    Next
    INDEX
    Explanations

    times 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_22/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
     duradero
    -1.28
    -1.27
    -1.24
    <i>
    -1.18
     that
    -1.16
    -1.11
     boneco
    -1.09
     lançamento
    -1.07
     atractiva
    -1.06
     vernünf
    -1.06
    POSITIVE LOGITS
     at
    1.66
     with
    1.32
     conster
    1.21
    ☆☆
    1.15
    了你
    1.13
    thenia
    1.13
    Zubereitung
    1.11
     ultime
    1.11
    Étymologie
    1.10
     допомогти
    1.09
    Activations Density 0.001%

    No Known Activations