© 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. 10-GEMMASCOPE-RES-131K
    7. 11918
    Prev
    Next
    INDEX
    Explanations

    MM followed by other text

    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_10/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
     Bedürfn
    -2.45
     dueño
    -2.36
    再度
    -2.36
     uſed
    -2.25
    渽
    -2.20
    ࿆
    -2.20
     configurações
    -2.17
    creenshot
    -2.17
     Unglück
    -2.17
     amassed
    -2.11
    POSITIVE LOGITS
    龗
    2.53
    嵎
    2.28
    われ
    2.25
    馓
    2.20
     processus
    2.20
    狁
    2.05
    IN
    2.03
     entraîne
    2.02
    鹟
    2.02
    ні
    2.00
    Activations Density 0.013%

    No Known Activations