© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9285
    Prev
    Next
    INDEX
    Explanations

    print statement with f-string

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

    The neuron fires on numeric tokens with embedded decimal points (e.g. DOIs, page or article identifiers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     `
    0.94
    `
    0.81
     `.
    0.79
     `,
    0.77
    =`
    0.76
    `.
    0.75
    )`
    0.75
    .`
    0.75
     (`
    0.74
    `).
    0.73
    POSITIVE LOGITS
     f
    1.47
     ف
    0.94
     fuck
    0.87
    f
    0.84
     fucking
    0.81
     sprintf
    0.75
    ("{}
    0.72
     ф
    0.71
     Fuck
    0.71
     fucked
    0.71
    Activations Density 0.011%

    No Known Activations