© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77549
    Prev
    Next
    INDEX
    Explanations

    finite element method simulation

    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
     Reinhold
    -0.72
    อล
    -0.72
    AJAS
    -0.69
    ucción
    -0.68
    fname
    -0.68
    őz
    -0.67
    さを
    -0.66
    酸
    -0.66
     Communion
    -0.66
    nolo
    -0.66
    POSITIVE LOGITS
     Galer
    1.64
     FEM
    1.45
     finite
    1.36
    Galer
    1.29
    FEM
    1.29
     Finite
    1.26
    Finite
    1.23
     discre
    1.13
     method
    1.13
    Fem
    1.11
    Activations Density 0.053%

    No Known Activations