© 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. 14821
    Prev
    Next
    INDEX
    Explanations

    request to beneficiary

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

    The neuron spikes on formulaic Biblical‐style phrasing—especially comparative or superlative constructions from Scripture (e.g. “Greater love hath no man than this,” “no other name under heaven,” etc.).

    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
    tracing
    0.87
    ^{*}}
    0.87
     restos
    0.84
     erreichte
    0.79
    inn
    0.78
    grund
    0.77
    trailing
    0.75
     Noch
    0.75
    }^{-
    0.75
     außerhalb
    0.75
    POSITIVE LOGITS
    日
    0.70
    ስ
    0.70
    氦
    0.70
    хі
    0.70
    俄
    0.70
    錦
    0.69
    Username
    0.68
    確か
    0.67
     méthod
    0.67
    قية
    0.66
    Activations Density 0.000%

    No Known Activations