© 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. 13416
    Prev
    Next
    INDEX
    Explanations

    meta-prefix

    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
    ла
    -2.88
     Their
    -2.63
    ↵↵
    -2.58
    齜
    -2.48
    所有人都
    -2.47
    氿
    -2.47
    CurtirCurtir
    -2.45
     ursprünglich
    -2.42
     sorprend
    -2.34
     zwölf
    -2.31
    POSITIVE LOGITS
    咴
    3.64
    壟
    3.34
     lancia
    2.86
    呖
    2.84
     itinéraire
    2.81
    ╿
    2.80
     ヶ
    2.75
    鑄
    2.70
    樑
    2.63
     bague
    2.58
    Activations Density 0.029%

    No Known Activations