© 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. 13556
    Prev
    Next
    INDEX
    Explanations

    delivery services

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

    The neuron responds most strongly to very common, high–frequency words (i.e. frequent English tokens).

    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
     ограниче
    0.78
     প্রদেশ
    0.76
     ligation
    0.72
     давления
    0.72
     confining
    0.72
    สำหรับการ
    0.70
     lessening
    0.70
    㸵
    0.67
    壃
    0.67
    <unused2123>
    0.67
    POSITIVE LOGITS
    0.86
    Volvo
    0.73
     miraculous
    0.69
     unanimously
    0.68
     प्रातः
    0.68
     Coca
    0.67
    +
    0.66
    0
    0.66
    כם
    0.65
     a
    0.65
    Activations Density 0.000%

    No Known Activations