© 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. 65232
    Prev
    Next
    INDEX
    Explanations

    motorhome, campervan, houseboat, scooter

    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
     honom
    -1.18
    responder
    -1.16
    taient
    -1.12
     mister
    -1.11
    Rode
    -1.10
     Ctr
    -1.09
    ılığı
    -1.09
     cioccolato
    -1.09
    诶
    -1.08
    了什么
    -1.06
    POSITIVE LOGITS
     {
    1.22
    ぐり
    1.05
    libur
    1.05
     móvel
    1.05
    へと
    1.03
     agradável
    1.02
     sää
    1.02
    Y
    1.01
    ubat
    1.01
    パック
    0.98
    Activations Density 0.024%

    No Known Activations