© 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. 64279
    Prev
    Next
    INDEX
    Explanations

    html tags and separators

    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
     shouldBe
    -0.86
     सेवा
    -0.81
     može
    -0.81
     Römer
    -0.80
     enhances
    -0.77
    &=&\
    -0.77
    Exeunt
    -0.76
    〢
    -0.75
    (ﾟ
    -0.75
     sirvió
    -0.75
    POSITIVE LOGITS
    without
    0.96
    HT
    0.93
     すぐ
    0.84
    pulseira
    0.82
    热门
    0.80
    立马
    0.79
    änien
    0.78
    tgz
    0.78
    could
    0.78
    was
    0.78
    Activations Density 0.001%

    No Known Activations