© 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. 3632
    Prev
    Next
    INDEX
    Explanations

    Hey Everyone

    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
    correlated
    -0.82
    🦋
    -0.81
    hampton
    -0.81
     Serv
    -0.78
    Oise
    -0.77
     pasajeros
    -0.76
    LUS
    -0.75
    天皇
    -0.75
     Sint
    -0.74
    nitro
    -0.73
    POSITIVE LOGITS
    わい
    0.81
    仔细
    0.75
    zkopf
    0.74
    setNew
    0.71
    eseed
    0.71
    jvm
    0.70
     kogo
    0.70
     NavController
    0.69
     возбу
    0.69
    ouncy
    0.68
    Activations Density 0.042%

    No Known Activations