© 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. 6455
    Prev
    Next
    INDEX
    Explanations

    debate or binding code

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

    This neuron selectively fires on tokens representing floating-point numbers (long decimal numerals).

    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
     künstler
    0.98
     elaborar
    0.92
     delicacies
    0.89
    ণে
    0.88
    🫂
    0.87
     racionais
    0.86
     luxuries
    0.84
     menentukan
    0.83
     ইপিআর
    0.82
    ☭
    0.81
    POSITIVE LOGITS
    ed
    0.85
    I
    0.77
     I
    0.76
    ↵
    0.74
    EN
    0.73
    SAS
    0.69
    en
    0.68
     to
    0.67
    挺
    0.66
     Hang
    0.66
    Activations Density 0.000%

    No Known Activations