© 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. 6313
    Prev
    Next
    INDEX
    Explanations

    Dear [name]

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

    The neuron strongly activates on date‐stamp lines (e.g. publication or upload dates), effectively detecting document timestamp metadata.

    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
    вов
    0.63
    iscono
    0.62
    ㅃ
    0.60
    ટું
    0.59
    ረሻ
    0.59
    сок
    0.59
     except
    0.58
    ্ল
    0.58
    fontWeight
    0.58
    з
    0.57
    POSITIVE LOGITS
     toda
    0.97
     Genoa
    0.83
     Kaspersky
    0.82
    lard
    0.80
     Georgetown
    0.80
     Preto
    0.80
     DLP
    0.80
    RICS
    0.80
    y
    0.80
     Montevideo
    0.79
    Activations Density 0.000%

    No Known Activations