© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6358
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on formal legal references and numbered statute citations (e.g. section numbers, code references, FIR numbers).

    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
     অস্ব
    0.73
     ढेर
    0.64
     скри
    0.60
    唏
    0.59
    írez
    0.58
     অবা
    0.58
    靥
    0.57
     spectrophot
    0.57
    aphazard
    0.56
    罩
    0.55
    POSITIVE LOGITS
     crimes
    1.54
     felony
    1.53
     offences
    1.52
     offenses
    1.52
     felonies
    1.45
     punishable
    1.44
     offense
    1.42
     offence
    1.41
     Felony
    1.40
     Offences
    1.38
    Activations Density 0.258%

    No Known Activations