© 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. 31-GEMMASCOPE-2-RES-16K
    7. 7507
    Prev
    Next
    INDEX
    Explanations

    reporting problem that

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

    Neuron 4 looks for formal reporting or notification language—words and phrases about reporting, informing, sending, and official statements.

    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_31_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
    ⏬
    0.58
     elution
    0.58
     অর্জন
    0.56
     एल्
    0.52
     pripre
    0.52
    💍
    0.51
     తెర
    0.50
     diffract
    0.49
    翦
    0.49
     exile
    0.49
    POSITIVE LOGITS
     complaint
    2.69
     Complaint
    2.55
     complaints
    2.53
     complain
    2.41
    Complaint
    2.33
     Complaints
    2.31
     शिकायत
    2.25
     complaining
    2.23
     complains
    2.23
     complained
    2.16
    Activations Density 0.492%

    No Known Activations