© 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. 24-GEMMASCOPE-2-RES-16K
    7. 6220
    Prev
    Next
    INDEX
    Explanations

    pay day

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

    The neuron strongly responds to numeric tokens (e.g. years, page numbers, measurements, or other numbers in citations).

    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_24_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
    ты
    0.93
    сным
    0.91
    ों
    0.89
    мын
    0.87
     sterk
    0.85
    '
    0.84
     MRD
    0.81
    сы
    0.79
    емых
    0.79
    seid
    0.79
    POSITIVE LOGITS
    Oc
    0.72
     extraordinaire
    0.71
    //
    0.70
    apeutics
    0.68
     વિ
    0.68
    یو
    0.67
    ิง
    0.67
     involves
    0.65
     pares
    0.65
    )!
    0.65
    Activations Density 0.000%

    No Known Activations