© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59506
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    <h4>
    -0.74
    смотря
    -0.73
    fav
    -0.72
    LEIA
    -0.72
    zus
    -0.71
    },"
    -0.71
    :[{
    -0.69
    шего
    -0.69
    역사
    -0.69
     Tas
    -0.69
    POSITIVE LOGITS
     desayuno
    0.91
     Öz
    0.85
     devin
    0.83
    浒
    0.82
     Villarreal
    0.81
    حت
    0.79
     calavera
    0.79
     despedida
    0.79
     Comunidad
    0.78
    meras
    0.78
    Activations Density 0.021%

    No Known Activations