© 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. 10-GEMMASCOPE-RES-131K
    7. 123470
    Prev
    Next
    INDEX
    Explanations

    kidnapped or abducted people

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

    The main thing this neuron does is find mentions of abduction events (e.g., kidnapping, hostage taking, ransom demands).

    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
     magasiner
    -1.44
    Build
    -1.34
    是他
    -1.32
    quiera
    -1.29
     xxvi
    -1.27
                
    -1.27
            
    -1.27
    <b>
    -1.26
    er
    -1.25
     =
    -1.23
    POSITIVE LOGITS
     inderdaad
    1.41
     необхідно
    1.29
     Bunun
    1.27
     действительно
    1.26
    Leírás
    1.25
     daarvoor
    1.24
    Tengo
    1.22
    蟜
    1.22
     That
    1.20
    當時
    1.20
    Activations Density 0.033%

    No Known Activations