© 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. 83194
    Prev
    Next
    INDEX
    Explanations

    Custom Membership Provider

    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
     Ե
    -0.76
    న్న
    -0.76
     Pixar
    -0.76
     LEGISL
    -0.75
     fiberglass
    -0.74
    partiet
    -0.72
    idio
    -0.71
    닐
    -0.71
     Disneyland
    -0.70
    Ingrédients
    -0.69
    POSITIVE LOGITS
    UserDetails
    1.02
    details
    0.98
    userdetails
    0.86
     details
    0.85
    userDetails
    0.80
     UserDetails
    0.79
     prinsip
    0.78
    imentos
    0.78
    ítima
    0.78
    зывы
    0.77
    Activations Density 0.002%

    No Known Activations