© 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. 3172
    Prev
    Next
    INDEX
    Explanations

    template, slot, view, content

    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
    ꯍ
    -0.87
    ówka
    -0.78
    البته
    -0.77
     descenso
    -0.75
     Startseite
    -0.74
    امکان
    -0.74
    wirt
    -0.71
    sighs
    -0.71
    kranz
    -0.71
    ennessee
    -0.71
    POSITIVE LOGITS
    slot
    1.18
    SLOT
    1.16
    template
    1.13
     content
    1.05
     template
    1.05
     slot
    1.05
    content
    1.02
     SLOT
    0.97
    Template
    0.97
    getTemplate
    0.96
    Activations Density 0.077%

    No Known Activations