© 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. 98844
    Prev
    Next
    INDEX
    Explanations

    aa, ae, ace

    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
    TypeMap
    -0.73
     g
    -0.71
     streamlined
    -0.69
     on
    -0.68
     depositphotos
    -0.68
     τι
    -0.67
     passion
    -0.67
     continuing
    -0.67
     premises
    -0.66
    かた
    -0.66
    POSITIVE LOGITS
     YC
    0.84
     MVC
    0.83
    alamualaikum
    0.80
    Faker
    0.79
    psu
    0.79
    ppas
    0.79
    loyee
    0.79
     inac
    0.77
    炱
    0.77
    ⁓
    0.77
    Activations Density 0.005%

    No Known Activations