© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65844
    Prev
    Next
    INDEX
    Explanations

    in possession of illicit items

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

    The neuron spotlights legal‐charge language, especially phrases about being charged, accused, or in possession of something.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parameters
    -0.75
     OPTIM
    -0.73
     piste
    -0.72
     separat
    -0.71
    榜
    -0.66
     boulangerie
    -0.66
    mitter
    -0.66
    かって
    -0.65
     groovy
    -0.65
     gw
    -0.64
    POSITIVE LOGITS
     possession
    4.06
    possession
    3.08
     Possession
    2.83
    Poss
    2.36
     possessing
    2.14
     posesión
    2.13
     possessed
    2.05
     possess
    2.03
     possessions
    1.91
     posses
    1.90
    Activations Density 0.023%

    No Known Activations