© 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. 34-GEMMASCOPE-RES-131K
    7. 63611
    Prev
    Next
    INDEX
    Explanations

    suspects and people arrested

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

    The neuron activates on terms related to legal detention and arrest procedures (e.g. arrest, custody, warrant, questioning).

    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
     PASSWORD
    -0.96
     Assessor
    -0.78
     Ithaca
    -0.76
    szer
    -0.76
     separa
    -0.75
    諺
    -0.75
     ades
    -0.75
     kz
    -0.74
     précis
    -0.73
     Nude
    -0.73
    POSITIVE LOGITS
     suspects
    2.17
     suspect
    2.17
     подозре
    1.61
     sospe
    1.45
     suspected
    1.42
     prime
    1.34
    嫌疑
    1.27
     Sus
    1.23
     interest
    1.18
     implicated
    1.13
    Activations Density 0.024%

    No Known Activations