© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99416
    Prev
    Next
    INDEX
    Explanations

    your website embed

    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
     seguire
    -0.73
    
    -0.71
     torchvision
    -0.68
     luon
    -0.67
    avor
    -0.64
    AnimationsModule
    -0.64
     MINNESOTA
    -0.63
     Acerca
    -0.63
     rendimiento
    -0.63
    timent
    -0.63
    POSITIVE LOGITS
    odotus
    0.69
    臣
    0.68
    coming
    0.67
    remote
    0.67
    dB
    0.66
     стола
    0.65
     comple
    0.65
    己
    0.63
     Cline
    0.62
     coming
    0.61
    Activations Density 0.062%

    No Known Activations