© 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. 47639
    Prev
    Next
    INDEX
    Explanations

    java keywords and exceptions

    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
    assed
    -0.78
     alienation
    -0.74
    AUTHORS
    -0.70
    GREATER
    -0.68
     cuarent
    -0.68
     Manga
    -0.66
     Physica
    -0.66
    痊
    -0.65
     بک
    -0.65
     experienced
    -0.65
    POSITIVE LOGITS
    bca
    0.78
     REN
    0.78
    Wesley
    0.75
    kezik
    0.75
    epi
    0.74
     活
    0.73
    Nobody
    0.73
    adell
    0.72
     sun
    0.71
    FormsModule
    0.71
    Activations Density 0.058%

    No Known Activations