© 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. 63543
    Prev
    Next
    INDEX
    Explanations

    legal cases and code files

    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
     龍
    -0.77
     poorer
    -0.76
     genotyping
    -0.75
    UTR
    -0.73
     Hinds
    -0.73
    קים
    -0.72
     géant
    -0.72
     Segundo
    -0.72
    tagne
    -0.71
     Alameda
    -0.70
    POSITIVE LOGITS
     External
    0.92
     external
    0.86
    External
    0.82
    recep
    0.77
    external
    0.73
    毫无
    0.72
    ASONS
    0.71
    γά
    0.70
    onsa
    0.70
    =>{
    0.69
    Activations Density 0.023%

    No Known Activations