© 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. 103277
    Prev
    Next
    INDEX
    Explanations

    interface prefixes

    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
    arkiv
    -0.88
     then
    -0.80
    一樣
    -0.80
    tula
    -0.79
    來
    -0.79
    StateList
    -0.78
     infección
    -0.77
    назна
    -0.77
    czego
    -0.77
     seeing
    -0.75
    POSITIVE LOGITS
    REAT
    0.88
     terdengar
    0.79
    ight
    0.78
    ators
    0.77
    区間
    0.76
    زشکی
    0.75
     自定义
    0.75
    のだが
    0.74
     différentes
    0.74
    atures
    0.74
    Activations Density 0.029%

    No Known Activations