© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12537
    Prev
    Next
    INDEX
    Explanations

    code assignment or object access

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

    The neuron is specialized to detect floating‐point numeric literals (numbers containing decimal points).

    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
     ([
    0.67
    ',[
    0.64
    .:
    0.61
     -.
    0.60
    ₁.
    0.59
    .
    0.59
     ihn
    0.59
     ().
    0.58
    .,
    0.55
     %.
    0.55
    POSITIVE LOGITS
    ->
    0.75
    {'
    0.69
    ->_
    0.62
    전문
    0.59
     especialista
    0.59
    }";
    0.58
    ->__
    0.57
    )."
    0.57
     especialistas
    0.55
    ),"
    0.55
    Activations Density 0.004%

    No Known Activations