© 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. 73627
    Prev
    Next
    INDEX
    Explanations

    HTML entities like >

    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
    زين
    -0.85
     turist
    -0.84
     期
    -0.76
     Evid
    -0.76
     França
    -0.75
    dign
    -0.75
     stimuli
    -0.74
     conjug
    -0.74
     patria
    -0.74
     麺
    -0.73
    POSITIVE LOGITS
    post
    0.81
     post
    0.81
     segurança
    0.78
     blessé
    0.78
     logros
    0.75
     construção
    0.75
    瀆
    0.75
     ujednoznacz
    0.75
    zewod
    0.75
     следует
    0.75
    Activations Density 0.020%

    No Known Activations