© 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. 34-GEMMASCOPE-RES-131K
    7. 11988
    Prev
    Next
    INDEX
    Explanations

    court case submissions and decisions

    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_34/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
    沙发
    -0.77
     istället
    -0.65
    月号
    -0.65
    xn
    -0.64
    issons
    -0.63
    gnąć
    -0.63
    ใจ
    -0.63
    の記事
    -0.62
    timestamps
    -0.61
     Hima
    -0.61
    POSITIVE LOGITS
    getP
    0.79
     symb
    0.78
     الحره
    0.68
    ིག་
    0.68
    ADJ
    0.68
     dibangun
    0.68
     Grossman
    0.68
     Correa
    0.66
    capa
    0.66
     Coronel
    0.65
    Activations Density 0.056%

    No Known Activations