© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40356
    Prev
    Next
    INDEX
    Explanations

    release or parole

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

    The neuron activates on words and tokens that indicate release from custody or prison (e.g., freed, released, bail, parole).

    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
     I
    -1.70
    aimeJ
    -1.38
    mybatisplus
    -1.34
    stdbool
    -1.30
    繽
    -1.23
     sabem
    -1.23
    з
    -1.22
    onViewCreated
    -1.22
     キャップ
    -1.21
    サイズは
    -1.20
    POSITIVE LOGITS
     useAppContext
    1.48
     "
    1.45
     after
    1.41
     Instead
    1.38
    Дорогие
    1.35
    欵
    1.34
     Oyun
    1.34
     identifies
    1.33
    "¿
    1.33
     meines
    1.31
    Activations Density 0.018%

    No Known Activations