© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100639
    Prev
    Next
    INDEX
    Explanations

    safety systems and emergency equipment

    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
     to
    -1.41
     peuvent
    -1.20
    cellence
    -1.16
     maaaring
    -1.16
    ‗
    -1.14
     podemos
    -1.13
     mogą
    -1.12
    hide
    -1.08
    毁灭
    -1.07
     can
    -1.06
    POSITIVE LOGITS
    ningens
    1.28
     animais
    1.19
     safety
    1.17
    山上
    1.17
     समय
    1.13
     sair
    1.13
     元素
    1.12
    Ҷ
    1.12
     отсут
    1.11
     parete
    1.11
    Activations Density 0.077%

    No Known Activations