© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5212
    Prev
    Next
    INDEX
    Explanations

    police report investigation

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

    The neuron fires strongly on tokens from formal legal reporting—dates, section numbers, police/FIR references, and other procedural or bureaucratic terminology.

    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
     government
    0.59
     सरकारच्या
    0.59
     gobiernos
    0.59
     सरकार
    0.58
    government
    0.58
     அமைச்ச
    0.57
     bureaucrats
    0.57
     wastewater
    0.56
     bureaucr
    0.56
     Houses
    0.56
    POSITIVE LOGITS
     suspects
    0.92
     suspect
    0.84
     confessed
    0.84
     आरोपियों
    0.77
     પોલીસે
    0.77
    Police
    0.75
     આરોપી
    0.75
     போலீசார்
    0.75
     वारदात
    0.75
     interrogated
    0.72
    Activations Density 0.090%

    No Known Activations