© 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. 76328
    Prev
    Next
    INDEX
    Explanations

    age, Mage, G, association, correlation

    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
    moto
    -0.75
    vdots
    -0.72
    ковый
    -0.72
     certain
    -0.71
    anha
    -0.71
     فلسطين
    -0.71
     творо
    -0.70
    discord
    -0.70
    dere
    -0.70
     sia
    -0.69
    POSITIVE LOGITS
     Greenhouse
    0.99
     électro
    0.91
    ēja
    0.90
     thăm
    0.88
     Expertise
    0.83
    expertise
    0.83
     čase
    0.83
    collapsed
    0.83
     Threat
    0.82
    kezi
    0.82
    Activations Density 0.031%

    No Known Activations