© 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. 57802
    Prev
    Next
    INDEX
    Explanations

    physics and forces

    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
     Cliente
    -0.90
     wunder
    -0.86
     bep
    -0.86
     trasc
    -0.85
    istisch
    -0.84
    )});
    -0.84
     eden
    -0.81
     reguli
    -0.81
     DSL
    -0.80
     eis
    -0.80
    POSITIVE LOGITS
     while
    0.89
     grocery
    0.86
     Earth
    0.84
     although
    0.84
     girl
    0.82
     Italy
    0.82
     subsystems
    0.77
     Jim
    0.76
     coaching
    0.75
    Hi
    0.75
    Activations Density 0.023%

    No Known Activations