© 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. 24-GEMMASCOPE-2-RES-16K
    7. 6517
    Prev
    Next
    INDEX
    Explanations

    describing situations and states

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

    The neuron strongly lights up on tokens that introduce or occur within subordinate “if/when/as…” clauses expressing conditions, durations, or purposes.

    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
    $
    0.73
    &
    0.72
    /
    0.71
    izzle
    0.69
    extrémité
    0.68
     Lounge
    0.67
    _
    0.67
     arguably
    0.66
    auto
    0.64
     Adult
    0.64
    POSITIVE LOGITS
     אנחנו
    1.13
     நாங்கள்
    0.99
     ພວກເຮົາ
    0.97
     jihad
    0.96
     usamos
    0.96
     Hezbollah
    0.96
    <unused2110>
    0.95
     Allah
    0.94
     saudara
    0.93
     Tuhan
    0.92
    Activations Density 0.015%

    No Known Activations