© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78917
    Prev
    Next
    INDEX
    Explanations

    gri or gris names

    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
    whole
    -0.88
     whole
    -0.82
    zzlies
    -0.74
     potencial
    -0.73
    ياً
    -0.71
     smaller
    -0.69
    的功能
    -0.66
     Insgesamt
    -0.65
     judged
    -0.65
    cznych
    -0.65
    POSITIVE LOGITS
     Gri
    0.99
    Gri
    0.98
     gri
    0.96
     Agric
    0.91
     Grun
    0.91
     GR
    0.88
    gri
    0.83
    グリ
    0.82
     гри
    0.79
    spli
    0.75
    Activations Density 0.017%

    No Known Activations