© 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. 57466
    Prev
    Next
    INDEX
    Explanations

    mathematical or date context

    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
    ående
    -0.98
    jointe
    -0.95
     who
    -0.91
    dicionado
    -0.91
    =["
    -0.90
     sahip
    -0.90
    distan
    -0.90
    ｕ
    -0.89
    ołnier
    -0.89
    lables
    -0.88
    POSITIVE LOGITS
    avocat
    1.01
    atmosphère
    0.96
    ハワイ
    0.93
    Assemblée
    0.85
    Endnotes
    0.82
     erwähnten
    0.81
    Beaucoup
    0.81
     bellissima
    0.80
     oppress
    0.79
    IMHO
    0.78
    Activations Density 0.004%

    No Known Activations