© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47023
    Prev
    Next
    INDEX
    Explanations

    free followed by software/os names

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

    The neuron strongly responds to occurrences of the capitalized word “Free” (as in Free Software, FreeBSD, FreeCAD, etc.).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    marginHorizontal
    -0.70
     essentially
    -0.69
     Internasional
    -0.68
    rentes
    -0.66
     invertebrates
    -0.66
    新款
    -0.65
     PRESENTED
    -0.64
     рослин
    -0.64
    نگار
    -0.63
    Jol
    -0.63
    POSITIVE LOGITS
    glut
    0.86
     xi
    0.85
    íí
    0.84
    Mysql
    0.79
    FORM
    0.79
     homens
    0.74
    jue
    0.74
    eaky
    0.73
    commander
    0.73
    ์ตูน
    0.73
    Activations Density 0.067%

    No Known Activations