© 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. 49515
    Prev
    Next
    INDEX
    Explanations

    FreeBSD and Unix variants

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

    The neuron is triggered by mentions of BSD (and related operating-system or license terms such as “FreeBSD,” “BSD,” “Linux,” copyright/license boilerplate).

    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
     Física
    -0.75
    łgor
    -0.69
     weiß
    -0.67
    Ֆ
    -0.67
    apyrus
    -0.67
    林
    -0.66
     hessen
    -0.66
    🇶
    -0.66
    vocab
    -0.65
     legno
    -0.65
    POSITIVE LOGITS
    BSD
    2.05
     BSD
    1.91
    bsd
    1.59
     Unix
    1.58
     UNIX
    1.51
    UNIX
    1.20
     unix
    1.12
    Unix
    1.06
     Operating
    0.99
    unix
    0.92
    Activations Density 0.229%

    No Known Activations