© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 115846
    Prev
    Next
    INDEX
    Explanations

    court case details and dates

    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
    vägen
    -0.76
    uego
    -0.73
    衬衫
    -0.70
    вали
    -0.69
     য
    -0.68
    inki
    -0.68
     Ruk
    -0.68
    ERTY
    -0.66
     esoteric
    -0.66
    发货
    -0.66
    POSITIVE LOGITS
     生成
    0.69
    山下
    0.68
    谚
    0.67
    那时
    0.66
     SHARE
    0.65
    才能
    0.65
     бан
    0.64
    _),
    0.61
     Theologie
    0.60
     actuación
    0.60
    Activations Density 0.059%

    No Known Activations