© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113724
    Prev
    Next
    INDEX
    Explanations

    possession of

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

    The neuron activates on occurrences of the word “possession,” as in legal or criminal‐context mentions of someone being 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_10/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
    or
    -3.08
    your
    -3.03
    x
    -2.95
    琑
    -2.86
    梘
    -2.81
     fler
    -2.78
    y
    -2.78
    猡
    -2.75
    猻
    -2.75
    So
    -2.66
    POSITIVE LOGITS
    ↵
    4.44
     Importantly
    2.95
     Also
    2.81
     Furthermore
    2.81
    灩
    2.70
    <bos>
    2.67
     soothe
    2.66
     Again
    2.64
    งิน
    2.58
     Notably
    2.58
    Activations Density 0.005%

    No Known Activations