© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107263
    Prev
    Next
    INDEX
    Explanations

    setting edit triggers

    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
     Gautam
    -0.77
    𝘨
    -0.75
    啃
    -0.75
    lione
    -0.73
    ❗️
    -0.72
     daž
    -0.71
    chule
    -0.71
    ❗
    -0.71
     dropdown
    -0.71
    cader
    -0.71
    POSITIVE LOGITS
    setObjectName
    1.48
    ᴋ
    0.99
     céramique
    0.81
    ineno
    0.76
    ulaires
    0.75
    inaison
    0.74
    udo
    0.74
    ✶
    0.73
     object
    0.72
    ied
    0.71
    Activations Density 0.003%

    No Known Activations