© 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. 22-GEMMASCOPE-RES-131K
    7. 9829
    Prev
    Next
    INDEX
    Explanations

    acts of stealing

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

    The neuron activates on words denoting acts of theft (e.g. steal, stole, stealing).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     evoked
    -0.91
     royaume
    -0.88
    全て
    -0.86
     zcela
    -0.86
     populaires
    -0.85
    すべて
    -0.85
    ⸙
    -0.84
    ровая
    -0.82
     YANG
    -0.82
     learnt
    -0.82
    POSITIVE LOGITS
     from
    2.08
     steals
    1.17
     borrow
    1.07
     از
    1.06
     steal
    1.03
     chances
    1.01
    ustus
    0.99
     glances
    0.95
    thats
    0.95
    from
    0.94
    Activations Density 0.028%

    No Known Activations