© 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. 57602
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on Fortran source‐code constructs—especially type declarations (integer, real, parameter), allocatable arrays, and related allocation and parallel directives.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ongeza
    -0.82
    ="@
    -0.74
    äng
    -0.73
    getBoolean
    -0.73
     PyObject
    -0.72
    hatenablog
    -0.71
    строи
    -0.71
    asticity
    -0.71
     кровати
    -0.71
    THURSDAY
    -0.70
    POSITIVE LOGITS
    (/
    1.02
     ASSOCIATED
    1.01
     barra
    0.89
     prese
    0.82
     (/
    0.82
     مشاور
    0.81
    umoj
    0.81
    &
    0.80
     trim
    0.79
    associated
    0.77
    Activations Density 0.024%

    No Known Activations