© 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. 31088
    Prev
    Next
    INDEX
    Explanations

    hailing from

    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
    uncu
    -0.77
     Pháp
    -0.76
    errcode
    -0.76
     Existenz
    -0.75
    hishek
    -0.75
    hexyl
    -0.74
    ToHex
    -0.74
    됨
    -0.73
    hoten
    -0.73
    лё
    -0.72
    POSITIVE LOGITS
     hails
    5.41
     hail
    5.16
     hailed
    3.89
     Hail
    2.89
    hail
    2.86
    Hail
    2.86
     ha
    2.56
     berasal
    2.33
    ailing
    2.27
     hale
    2.23
    Activations Density 0.163%

    No Known Activations