© 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. 106987
    Prev
    Next
    INDEX
    Explanations

    preventing dirt, heat, or damage

    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
    цію
    -0.97
     richt
    -0.82
    wkt
    -0.80
    ficas
    -0.79
    网红
    -0.77
     Cloudy
    -0.77
    𝑲
    -0.77
    illères
    -0.77
     Outbreak
    -0.76
     Refund
    -0.74
    POSITIVE LOGITS
     rain
    2.14
     moisture
    2.06
     rainwater
    1.95
     sunlight
    1.88
     wind
    1.49
    雨
    1.48
     heat
    1.48
     dirt
    1.48
    rain
    1.45
     water
    1.43
    Activations Density 0.068%

    No Known Activations