© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118890
    Prev
    Next
    INDEX
    Explanations

    Objective-C `alloc` calls

    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
    Negative Logits
    »։
    -0.88
     Saltar
    -0.86
     yoktur
    -0.84
    பி
    -0.83
    ++){
    -0.83
    )$,
    -0.82
    idden
    -0.78
    xins
    -0.78
    ()){
    -0.75
     thriller
    -0.75
    POSITIVE LOGITS
     modific
    0.73
    chrono
    0.71
     plass
    0.70
    ICO
    0.70
     Ventura
    0.69
    ""
    0.69
     Seis
    0.68
     mura
    0.68
    .../
    0.68
    whatever
    0.67
    Activations Density 0.175%

    No Known Activations