© 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. 54326
    Prev
    Next
    INDEX
    Explanations

    court followed by of

    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
     and
    -0.85
    /*!
    -0.85
    iempo
    -0.84
    螃蟹
    -0.81
    ところに
    -0.81
     tarifleri
    -0.81
    蕎
    -0.79
    ϖ
    -0.76
     società
    -0.76
     deformity
    -0.75
    POSITIVE LOGITS
     judges
    1.57
     judge
    1.51
     bench
    1.20
     sitting
    1.17
     Judge
    1.16
     JUDGE
    1.13
    Judge
    1.13
    judge
    1.13
     Judges
    1.13
    Judges
    1.05
    Activations Density 0.250%

    No Known Activations