© 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. 30461
    Prev
    Next
    INDEX
    Explanations

    make ends meet

    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
     Riccardo
    -0.71
     Renata
    -0.68
    PSY
    -0.68
    formulario
    -0.66
     exports
    -0.65
    tioned
    -0.64
    ticed
    -0.64
    irac
    -0.63
    bounding
    -0.62
    マイズ
    -0.62
    POSITIVE LOGITS
     ピ
    0.73
    quef
    0.71
    imread
    0.68
    屁
    0.67
     Messiah
    0.66
    COUNTS
    0.66
     сайті
    0.65
    Ability
    0.65
     treatises
    0.65
     Sabbath
    0.64
    Activations Density 0.090%

    No Known Activations