© 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. 10-GEMMASCOPE-RES-131K
    7. 100870
    Prev
    Next
    INDEX
    Explanations

    mathematical and code variables

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

    single-letter variable names in mathematical or programming code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on short identifier names (especially single‐letter variable names) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     but
    -2.03
    f
    -1.81
    ława
    -1.81
    ut
    -1.61
    k
    -1.54
    rn
    -1.53
    but
    -1.49
     obiettivi
    -1.48
    pso
    -1.47
    avaient
    -1.47
    POSITIVE LOGITS
     you
    2.13
    ).
    1.67
     podem
    1.65
     algunos
    1.64
    ruguay
    1.59
     would
    1.59
    camisas
    1.59
     which
    1.57
     casada
    1.55
     algunas
    1.54
    Activations Density 0.038%

    No Known Activations