© 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. 22-GEMMASCOPE-RES-131K
    7. 53969
    Prev
    Next
    INDEX
    Explanations

    authors speaking about personal experience

    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_22/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
    ;
    -1.08
     this
    -0.98
     but
    -0.97
    瞠
    -0.94
     S
    -0.94
    よい
    -0.92
     doz
    -0.91
     W
    -0.91
    sizePolicy
    -0.90
     رسد
    -0.90
    POSITIVE LOGITS
    ễm
    1.05
     protège
    1.04
    жных
    1.04
    ,
    1.03
     hieronder
    1.00
    ziele
    1.00
     suivez
    0.98
     appelez
    0.98
    junior
    0.97
     nomme
    0.97
    Activations Density 0.095%

    No Known Activations