© 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. 1569
    Prev
    Next
    INDEX
    Explanations

    what's a question

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

    This neuron activates on promotional or sales‐pitch language—calls to action advertising services or deals.

    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
     is
    0.61
     described
    0.61
     enjoined
    0.61
     and
    0.58
     may
    0.58
    Trusted
    0.58
    0.56
     l
    0.55
     dreamed
    0.54
     in
    0.54
    POSITIVE LOGITS
    áját
    0.99
    allenges
    0.98
     Quadrupèdes
    0.95
    éraux
    0.90
    ának
    0.89
    ákat
    0.89
    cailles
    0.86
    ulières
    0.86
    ámicas
    0.86
    adisu
    0.85
    Activations Density 0.022%

    No Known Activations