© 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. 2647
    Prev
    Next
    INDEX
    Explanations

    number, code, financial, or technical terms

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

    The neuron consistently fires on words from software license and copyright/distribution notices (e.g. “copyright,” “redistribute,” “disclaimer,” “license,” “conditions,” “code,” “rights”).

    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
    tran
    -0.72
    TRAN
    -0.69
     quotidienne
    -0.67
    垠
    -0.65
     kaufen
    -0.65
     jūs
    -0.64
     ešte
    -0.64
     svoju
    -0.64
    TRA
    -0.63
     tran
    -0.62
    POSITIVE LOGITS
     Gravel
    0.75
    驭
    0.71
     Ninth
    0.69
     XC
    0.68
     Sixth
    0.67
    RequestMapping
    0.66
     CUN
    0.66
     IPO
    0.66
     flanked
    0.66
     fumble
    0.65
    Activations Density 0.064%

    No Known Activations