© 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. 79509
    Prev
    Next
    INDEX
    Explanations

    Manila locations

    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
    驷
    -0.84
    alanya
    -0.81
     bite
    -0.80
    ント
    -0.79
     CMT
    -0.77
    bite
    -0.76
     aliquot
    -0.75
     Marav
    -0.74
    buje
    -0.74
    confirm
    -0.74
    POSITIVE LOGITS
    putString
    0.71
    妳
    0.70
     создание
    0.70
    ÍAS
    0.66
     éves
    0.66
    resep
    0.66
    首都
    0.65
     chua
    0.65
     republiky
    0.65
     describes
    0.64
    Activations Density 0.029%

    No Known Activations