© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 4692
    Prev
    Next
    INDEX
    Explanations

    shift in innovative prompt

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

    This neuron detects tokens belonging to “https://” (secure URL) strings.

    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
    几年
    0.89
     vissa
    0.82
     również
    0.80
    펀
    0.79
    řich
    0.78
    realistic
    0.78
    rä
    0.77
     wyjątk
    0.77
     Brü
    0.77
     Verhältnis
    0.76
    POSITIVE LOGITS
    سات
    0.71
    кета
    0.70
    ses
    0.68
     margarita
    0.67
     translation
    0.67
    <0xA8>
    0.66
    I
    0.66
    ет
    0.64
     lollipop
    0.63
    >{
    0.63
    Activations Density 0.000%

    No Known Activations