© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63876
    Prev
    Next
    INDEX
    Explanations

    places followed by store or shop

    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
     футболка
    -1.20
    ઃ
    -1.09
     lanza
    -1.03
     täglich
    -1.00
    顔が
    -0.98
     zuhause
    -0.97
     präsenti
    -0.97
     beispielsweise
    -0.94
    通常の
    -0.94
     niega
    -0.93
    POSITIVE LOGITS
    unción
    1.05
    bestos
    1.00
     clinic
    1.00
    lında
    0.98
    اين
    0.96
     shop
    0.95
    ♫
    0.95
     station
    0.94
    性价比
    0.94
     emp
    0.93
    Activations Density 0.068%

    No Known Activations