© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 2867
    Prev
    Next
    INDEX
    Explanations

    young followed by name or noun

    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
     Mots
    -0.87
    捡
    -0.79
    Více
    -0.77
    HAL
    -0.74
    <0xC7>
    -0.74
    ←
    -0.74
     Tartar
    -0.73
     Bayern
    -0.72
    Lounge
    -0.72
    ppur
    -0.72
    POSITIVE LOGITS
     Young
    0.97
     verwe
    0.85
    Young
    0.79
    codiles
    0.71
     YOUNG
    0.71
     plaat
    0.71
     Rpc
    0.70
     YO
    0.69
     sad
    0.68
     экологи
    0.68
    Activations Density 0.022%

    No Known Activations