© 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. 58375
    Prev
    Next
    INDEX
    Explanations

    importing namespaces in code

    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
    ņem
    -0.85
     (€
    -0.83
    (){}
    -0.78
    هره
    -0.75
    头上
    -0.74
    SSI
    -0.73
     cmake
    -0.73
     pulmonary
    -0.73
     щодо
    -0.73
     būtų
    -0.72
    POSITIVE LOGITS
     liberating
    0.81
     ഗ
    0.78
    pezi
    0.76
     larmes
    0.76
    כי
    0.76
    gica
    0.76
    Gall
    0.75
     alien
    0.74
     liberate
    0.74
    さて
    0.72
    Activations Density 0.006%

    No Known Activations