© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 25721
    Prev
    Next
    INDEX
    Explanations

    lists and details

    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
    色々な
    -0.85
    ・・・・・・・・
    -0.82
    ピッタリ
    -0.81
    きれいな
    -0.81
    楽しめます
    -0.78
    本当の
    -0.78
     كلام
    -0.78
    Limiter
    -0.78
    ihe
    -0.78
    Materiale
    -0.77
    POSITIVE LOGITS
    中心
    1.15
    Info
    1.15
    list
    1.12
     list
    1.09
     introducción
    1.05
    Detail
    1.02
    Management
    0.98
    detail
    0.98
    info
    0.97
    List
    0.94
    Activations Density 0.016%

    No Known Activations