© 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. 83416
    Prev
    Next
    INDEX
    Explanations

    processes and states

    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
    那种
    -1.18
     desirable
    -1.08
    ra
    -1.02
     um
    -1.02
    爲
    -0.99
    opti
    -0.98
     estatal
    -0.97
    悽
    -0.97
    全世界
    -0.96
    tabil
    -0.96
    POSITIVE LOGITS
    lized
    1.42
    izing
    1.40
    izes
    1.36
     ребенка
    1.27
    lization
    1.27
    tization
    1.25
    izable
    1.23
    ее
    1.18
     critica
    1.16
     ребенку
    1.14
    Activations Density 0.194%

    No Known Activations