© 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. 130922
    Prev
    Next
    INDEX
    Explanations

    model brand followed by category

    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
    远离
    -1.28
    彼らの
    -1.27
     sortes
    -1.27
    ţiile
    -1.25
    mma
    -1.25
    魑
    -1.23
     astuces
    -1.20
    änomen
    -1.19
    valents
    -1.19
     débit
    -1.18
    POSITIVE LOGITS
    いいですね
    1.27
     ~=
    1.22
     Terbaru
    1.16
    鏄
    1.15
     Ternyata
    1.15
     Хи
    1.14
    Salu
    1.13
    大丈夫です
    1.13
     Manusia
    1.13
    鉀
    1.13
    Activations Density 0.038%

    No Known Activations