© 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. 10-GEMMASCOPE-RES-131K
    7. 44197
    Prev
    Next
    INDEX
    Explanations

    cooking vessels

    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
    鹂
    -1.60
     مشارکت‌کنندگان
    -1.58
    arão
    -1.55
    ----</
    -1.42
    while
    -1.41
    служба
    -1.39
    ')],
    -1.38
     اینکه
    -1.35
    ,“
    -1.35
    _)
    -1.33
    POSITIVE LOGITS
    ↵↵
    1.70
     educativos
    1.40
     activo
    1.31
     humanas
    1.31
     aspecto
    1.31
    ご相談
    1.30
     tangled
    1.28
    炱
    1.28
     it
    1.26
     skup
    1.24
    Activations Density 0.006%

    No Known Activations