© 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. 24-GEMMASCOPE-2-RES-16K
    7. 4327
    Prev
    Next
    INDEX
    Explanations

    checks variable type

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

    The neuron is primarily detecting numeric tokens (i.e. tokens made up of digits).

    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
     departamento
    0.90
    芏
    0.89
    鄧
    0.84
    tevõ
    0.82
     departamentos
    0.80
     beschäft
    0.80
    ikova
    0.80
     Dahmer
    0.79
    <unused53>
    0.79
     Higgins
    0.79
    POSITIVE LOGITS
    }\
    0.72
    Page
    0.71
     corrobor
    0.68
     enclosing
    0.65
     coincides
    0.64
     else
    0.64
    सोई
    0.63
    PY
    0.62
    iles
    0.62
     induces
    0.61
    Activations Density 0.002%

    No Known Activations