© 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. 77881
    Prev
    Next
    INDEX
    Explanations

    image tag, programming class, or Hindu

    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
     oddly
    -0.94
     troubling
    -0.89
    legung
    -0.83
     pena
    -0.80
     湯
    -0.78
     peat
    -0.77
    仕
    -0.77
     unrelenting
    -0.76
    شرات
    -0.76
    UINT
    -0.76
    POSITIVE LOGITS
     schli
    0.88
     confirmó
    0.85
     anunció
    0.85
    进行
    0.84
    semana
    0.83
     erhi
    0.81
     overarching
    0.80
     Erfahrung
    0.80
     presentó
    0.79
     …..
    0.79
    Activations Density 0.000%

    No Known Activations