© 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. 59615
    Prev
    Next
    INDEX
    Explanations

    code snippets or assignments

    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
     Entdecke
    -0.90
    Что
    -0.84
     accedi
    -0.82
     scottish
    -0.81
     pravidel
    -0.81
     efficaces
    -0.80
    piej
    -0.80
     vhodné
    -0.79
    Tämä
    -0.78
    Crear
    -0.77
    POSITIVE LOGITS
    =`
    0.96
     окру
    0.88
     esper
    0.88
     atra
    0.86
     onOptions
    0.84
     claus
    0.81
    +'</
    0.79
    +='
    0.79
    sendKeys
    0.79
     poli
    0.79
    Activations Density 0.087%

    No Known Activations